© 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. 112751
    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
    ç¥ī
    -0.22
    sequent
    -0.22
    Pet
    -0.21
    овал
    -0.21
    combination
    -0.21
     Arbeit
    -0.21
    é£İæ°´
    -0.21
    åħ¨ä½ĵåijĺå·¥
    -0.20
    è¿Ļå°±æĺ¯
    -0.20
     Camden
    -0.20
    POSITIVE LOGITS
    ÂŃs
    0.24
    oller
    0.22
    agit
    0.22
    åľºåĿĩ
    0.22
    å·©
    0.22
     ste
    0.21
     Naming
    0.21
    éĵ¢
    0.21
    fixtures
    0.21
    ervatives
    0.20
    Activations Density 0.001%

    No Known Activations

    This feature has no known activations.