© 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. 87237
    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
    åij½
    -0.26
    asting
    -0.26
    çļĦæķ´ä½ĵ
    -0.25
    izations
    -0.25
    Ĩµ
    -0.24
    çļĦæ¦Ĥ念
    -0.24
    lesen
    -0.24
    å°±å¦ĤåIJĮ
    -0.24
    /function
    -0.24
     Crop
    -0.23
    POSITIVE LOGITS
    cene
    0.29
    ndl
    0.26
     Valk
    0.25
    ucci
    0.25
    _decl
    0.25
    quals
    0.25
    å¤©åºľ
    0.24
    åħ³äºİæĪij们
    0.24
     Belgi
    0.24
    alia
    0.24
    Activations Density 0.028%

    No Known Activations

    This feature has no known activations.