© 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. 130515
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
     pick
    -0.31
    CCI
    -0.31
    çĶĦ
    -0.30
    ewis
    -0.28
    æĭ¾
    -0.26
    lük
    -0.25
     picks
    -0.25
    èĺħ
    -0.24
    pick
    -0.23
    ifik
    -0.23
    POSITIVE LOGITS
    Borders
    0.26
     Bel
    0.25
     BEL
    0.25
    è´¨éĩıåĴĮ
    0.25
    arna
    0.23
    è´Ŀå°Ķ
    0.23
    åı£æ°´
    0.23
    Bel
    0.23
    BEL
    0.23
     rio
    0.23
    Activations Density 0.005%

    No Known Activations

    This feature has no known activations.