© 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. 33-TRANSCODER-HP
    7. 53764
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_33.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.33.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ä¸Ń央
    -0.26
     MTV
    -0.25
     VIN
    -0.24
    FirstResponder
    -0.24
    _CNTL
    -0.24
     Ridley
    -0.24
    åĩĮæĻ¨
    -0.24
    èįŀ
    -0.23
    @Inject
    -0.23
    emony
    -0.23
    POSITIVE LOGITS
    ©
    0.26
    suit
    0.26
    ndo
    0.25
     AD
    0.25
     gradu
    0.24
    /devices
    0.24
    ç»Ī究
    0.24
    æĤłæĤł
    0.23
     toler
    0.23
    è¿ĩ渡
    0.23
    Activations Density 0.006%

    No Known Activations

    This feature has no known activations.