© 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. 39387
    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
    çĸ£
    -0.31
    Mine
    -0.28
     mee
    -0.25
     Boo
    -0.24
    æľīç§į
    -0.24
    oire
    -0.24
    å¿ħ
    -0.24
    éļ¾å¾Ĺ
    -0.24
     поÑĤеÑĢÑı
    -0.24
     Trouble
    -0.23
    POSITIVE LOGITS
    _eng
    0.29
     retros
    0.28
    éĻ¢éĻ¢éķ¿
    0.27
     hạ
    0.25
    ispers
    0.25
    -eng
    0.25
    黨
    0.25
    _width
    0.24
    enthal
    0.24
    pace
    0.24
    Activations Density 23.852%

    No Known Activations

    This feature has no known activations.