© 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. 22-TRANSCODER-HP
    7. 112729
    Prev
    Next
    INDEX
    Explanations

    Completion of an action

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_22.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.22.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    åĨĻä¸ĭ
    -0.26
    Sid
    -0.25
    itional
    -0.25
    éĨĴäºĨ
    -0.24
     RequestOptions
    -0.24
    åŀŃ
    -0.24
    REM
    -0.24
    obili
    -0.24
    bole
    -0.24
    isma
    -0.24
    POSITIVE LOGITS
     priv
    0.32
    ucid
    0.29
     Priv
    0.27
     Anth
    0.24
     PH
    0.24
    unch
    0.24
    \\"
    0.24
    inite
    0.24
     unk
    0.24
     unknown
    0.24
    Activations Density 0.011%

    No Known Activations