© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 4-TRANSCODER-HP
    7. 2
    Prev
    Next
    INDEX
    Explanations

    Marr

    np_max-act · gemini-2.0-flash

    proper nouns featuring the character sequence “Marr” or “Maz,” especially in names of people or places.

    oai_token-act-pair · gpt-5Triggered by @liuliujiujiu05
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_4.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.4.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    iais
    -0.28
    ç´łé£Ł
    -0.26
    æµ·
    -0.24
    ainty
    -0.24
    าà¸ĩ
    -0.24
    ya
    -0.24
    èĢģåħµ
    -0.24
    ais
    -0.23
    	EIF
    -0.23
    ROID
    -0.23
    POSITIVE LOGITS
    éĶĻè¿ĩäºĨ
    0.28
     enclosing
    0.28
    嵯
    0.27
    ople
    0.27
    çĨĻ
    0.27
    hana
    0.25
    osing
    0.25
    lod
    0.25
    éľĢè¦ģçĶ¨
    0.24
     Batt
    0.24
    Activations Density 0.037%

    No Known Activations