© 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. 27-TRANSCODER-HP
    7. 57401
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_27.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.27.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    æ¶Ī失äºĨ
    -0.29
    æ·ĸ
    -0.28
    .subscribe
    -0.26
    cales
    -0.26
    arton
    -0.25
    uant
    -0.25
     Transitional
    -0.25
    escape
    -0.25
    çļĩåIJİ
    -0.25
    åľ¨è¿ĩ渡
    -0.25
    POSITIVE LOGITS
    beck
    0.30
    IX
    0.28
    bage
    0.28
    óst
    0.27
    handled
    0.26
    _IV
    0.25
    ix
    0.25
    ät
    0.24
    éŁŃ
    0.24
    AKE
    0.24
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.