© 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. 25-TRANSCODER-HP
    7. 108812
    Prev
    Next
    INDEX
    Explanations

    code snippets

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_25.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.25.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     panc
    -0.30
    åĪ©çī©
    -0.28
    anky
    -0.28
    åľ°è²Į
    -0.26
    _dash
    -0.25
    _Surface
    -0.25
     WWW
    -0.24
     toughest
    -0.24
    lcd
    -0.23
    lagen
    -0.23
    POSITIVE LOGITS
    å´ĩ
    0.30
     Fuj
    0.28
    åįķåħĥ
    0.26
    æŀģ
    0.26
    ppe
    0.26
     Ag
    0.26
    éħį
    0.25
    溱
    0.25
     opening
    0.25
     pylint
    0.25
    Activations Density 0.137%

    No Known Activations