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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 9-TRANSCODER-HP
    7. 29906
    Prev
    Next
    INDEX
    Explanations

    wrote

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_9.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.9.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    egis
    -0.28
    æ£Ĵ
    -0.27
    oust
    -0.27
    LLU
    -0.25
    unan
    -0.25
    gars
    -0.25
    cery
    -0.25
    ullah
    -0.24
    pike
    -0.24
    gas
    -0.24
    POSITIVE LOGITS
    ware
    0.29
     undert
    0.26
    âĢ¿
    0.26
    å¼Ł
    0.26
    aña
    0.26
    çĻ½éĵ¶
    0.26
    äng
    0.25
     Skill
    0.25
    UID
    0.25
    ä¸Ģ声
    0.24
    Activations Density 0.250%

    No Known Activations