© 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. 88557
    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
    uant
    -0.29
    åĤĻ
    -0.25
    tte
    -0.25
    aston
    -0.25
    åįģä½Ļå¹´
    -0.23
     verm
    -0.23
     hors
    -0.23
    åºŁ
    -0.23
    éĢģå¾Ģ
    -0.23
    urf
    -0.23
    POSITIVE LOGITS
    第äºĮç§į
    0.23
    /ion
    0.22
     steps
    0.22
    chematic
    0.22
    åıįæŃ£
    0.22
    é»ı
    0.22
     Gaz
    0.21
    Adv
    0.21
    ambiguous
    0.21
    istrate
    0.21
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.