© 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. 14-TRANSCODER-HP
    7. 41094
    Prev
    Next
    INDEX
    Explanations

    Special characters and symbols

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_14.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.14.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ä¸ĭæīĭ
    -0.31
    å±Ģ
    -0.26
    çĬ¯è§Ħ
    -0.26
    ActionBar
    -0.24
    asting
    -0.24
    DialogTitle
    -0.24
    ?";↵
    -0.23
    çű
    -0.23
     buses
    -0.23
     truthful
    -0.23
    POSITIVE LOGITS
    æºħ
    0.26
    cdc
    0.26
    èĩªè±ª
    0.25
    顺
    0.24
    奢
    0.24
     xc
    0.24
    cd
    0.24
    vron
    0.24
    åı¸æ³ķ
    0.24
    ugi
    0.24
    Activations Density 1.559%

    No Known Activations