© 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. 35-TRANSCODER-HP
    7. 40400
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_35.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.35.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     threading
    -0.28
    \:
    -0.27
    ãĤ¹ãĤ¿ãĥ³
    -0.25
     nov
    -0.24
    orce
    -0.23
    resh
    -0.23
    æĨĶ
    -0.23
    vers
    -0.23
    ardo
    -0.23
    ä¸ĩ象
    -0.23
    POSITIVE LOGITS
    Behaviour
    0.27
    便
    0.27
     behaviour
    0.25
    åºĶçĶ¨æŁ¥çľĭ
    0.25
     males
    0.25
     leopard
    0.24
    便æĺ¯
    0.23
     Behaviour
    0.23
     counted
    0.23
    locs
    0.23
    Activations Density 17.668%

    No Known Activations

    This feature has no known activations.