© 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. 12-TRANSCODER-HP
    7. 23775
    Prev
    Next
    INDEX
    Explanations

    z

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_12.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.12.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ope
    -0.28
    sted
    -0.28
     Dover
    -0.27
    ä¸įèĥ½åĨį
    -0.26
    çĤĴä½ľ
    -0.25
    exact
    -0.25
     exact
    -0.25
    BUG
    -0.25
    轩
    -0.25
    ntag
    -0.24
    POSITIVE LOGITS
     destin
    0.27
    tical
    0.27
    (ed
    0.26
    asis
    0.25
    ä¸ĢæĶ¯
    0.24
    .getRoot
    0.24
    wechat
    0.24
    usal
    0.24
    ppelin
    0.24
     War
    0.24
    Activations Density 0.015%

    No Known Activations