© 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. 53896
    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
    aturity
    -0.28
    олж
    -0.26
    iant
    -0.26
     Salt
    -0.26
    antage
    -0.26
    æľīåħ³éĥ¨éŨ
    -0.25
    ransition
    -0.25
    ween
    -0.24
    å¸ĤåĢ¼
    -0.23
    Salt
    -0.23
    POSITIVE LOGITS
    uche
    0.27
    conj
    0.27
     lc
    0.26
    建设工ç¨ĭ
    0.26
    as
    0.26
    yet
    0.25
     clan
    0.25
     conj
    0.25
     Prem
    0.25
    eneg
    0.25
    Activations Density 0.006%

    No Known Activations

    This feature has no known activations.