© 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. 31-TRANSCODER-HP
    7. 18921
    Prev
    Next
    INDEX
    Explanations

    warn

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_31.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.31.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Controlled
    -0.28
     intox
    -0.27
    oÄŁlu
    -0.24
    æ¤ħ
    -0.24
    roc
    -0.24
    enheim
    -0.24
    ivol
    -0.24
     espos
    -0.24
    åıĹ
    -0.24
     zurück
    -0.23
    POSITIVE LOGITS
    about
    0.53
     about
    0.51
    >About
    0.40
    _about
    0.39
     ABOUT
    0.38
    ABOUT
    0.36
    éĩįå¤į
    0.35
    About
    0.34
     About
    0.34
    åħ³äºİ
    0.33
    Activations Density 0.104%

    No Known Activations