© 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. 98729
    Prev
    Next
    INDEX
    Explanations

    1

    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
    æ§ģ
    -0.27
    out
    -0.27
    å½ĵãģŁãĤĬ
    -0.26
    _GENERAL
    -0.26
    ;&
    -0.25
     seemed
    -0.24
    åĤį
    -0.23
     actually
    -0.23
    ichten
    -0.23
     formulated
    -0.22
    POSITIVE LOGITS
    /pp
    0.29
     Kis
    0.26
    /license
    0.26
    /null
    0.26
    nown
    0.25
    likely
    0.24
    plevel
    0.24
    थ
    0.24
     qualifying
    0.24
    gba
    0.24
    Activations Density 0.038%

    No Known Activations