© 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. 111851
    Prev
    Next
    INDEX
    Explanations

    code and programming

    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
    anke
    -0.26
    åħµåĽ¢
    -0.26
    大家éĥ½åľ¨
    -0.24
    terminate
    -0.24
    åħ¶å®ĥéĹ®é¢ĺ
    -0.24
    AuthService
    -0.24
    æĪijçľĭ
    -0.24
    authenticate
    -0.23
     appName
    -0.23
    ará
    -0.23
    POSITIVE LOGITS
    flo
    0.26
     obr
    0.26
     casts
    0.24
    åij¨å¹´
    0.24
    æĵį
    0.23
    /{{$
    0.23
     Flo
    0.23
    OMET
    0.23
    (si
    0.23
    å¼Ģåĩº
    0.23
    Activations Density 0.002%

    No Known Activations