© 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. 27-TRANSCODER-HP
    7. 9415
    Prev
    Next
    INDEX
    Explanations

    code/technical memos

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_27.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.27.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    pha
    -0.26
    .spawn
    -0.26
    ipo
    -0.26
     Tradable
    -0.26
     resign
    -0.25
    ameda
    -0.25
    GRA
    -0.24
    ãĤĩãģĨ
    -0.24
    neh
    -0.24
     Trials
    -0.24
    POSITIVE LOGITS
     pus
    0.26
    _Widget
    0.26
    roit
    0.25
    -rights
    0.25
     accessed
    0.25
    ucus
    0.24
     accessing
    0.24
    ãĥĢãĤ¤
    0.24
    æ°´åĪĨ
    0.24
     substances
    0.24
    Activations Density 0.002%

    No Known Activations