© 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. 33-TRANSCODER-HP
    7. 53595
    Prev
    Next
    INDEX
    Explanations

    intelligence

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_33.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.33.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    serter
    -0.30
    istring
    -0.28
    æĶ¯çº¿
    -0.28
    setLabel
    -0.27
    è·Ľ
    -0.27
    åĶ¾
    -0.27
    aska
    -0.25
    USERNAME
    -0.25
    spath
    -0.25
    OfString
    -0.25
    POSITIVE LOGITS
     quo
    0.38
    quot
    0.37
     quot
    0.36
    qu
    0.36
     powers
    0.35
    ,
    0.33
     powered
    0.33
     power
    0.32
     quotient
    0.31
     ↵
    0.31
    Activations Density 0.011%

    No Known Activations