© 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. 112026
    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
    ivas
    -0.30
     gap
    -0.28
    gap
    -0.28
    å·®è·Ŀ
    -0.27
    åģı
    -0.26
    缺åı£
    -0.26
    çŃĸ
    -0.25
    饵
    -0.25
    -gap
    -0.25
    agu
    -0.25
    POSITIVE LOGITS
    åıijæĶ¹å§Ķ
    0.27
    addons
    0.27
     dared
    0.26
     invent
    0.26
     Inc
    0.26
     feared
    0.23
    ãĤĤãģĨ
    0.23
    .
    0.23
    .mixin
    0.23
     Discounts
    0.23
    Activations Density 0.039%

    No Known Activations

    This feature has no known activations.