© 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. 40349
    Prev
    Next
    INDEX
    Explanations

    anything

    np_max-act-logits · gemini-2.0-flash
    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
     Acceler
    -0.30
     Mort
    -0.29
     Access
    -0.28
     Futures
    -0.28
     Connect
    -0.28
     Increment
    -0.27
     Enh
    -0.27
     Prem
    -0.27
     Incre
    -0.27
     Achie
    -0.27
    POSITIVE LOGITS
    ä¹Łåıªæľī
    0.33
     whichever
    0.30
     amongst
    0.30
     unwilling
    0.30
     rundown
    0.29
    ä¹Łåıªèĥ½
    0.28
    ä¹ŁéľĢè¦ģ
    0.28
    äºĨä¸ĭæĿ¥
    0.28
     compliment
    0.28
    0.27
    Activations Density 1.127%

    No Known Activations