© 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. 52963
    Prev
    Next
    INDEX
    Explanations

    actions/events

    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
    .",č↵
    -0.42
    ...",↵
    -0.39
    .",↵
    -0.38
    ."},↵
    -0.36
    ."),↵
    -0.35
    :",↵
    -0.34
    .`,↵
    -0.34
    ",↵↵
    -0.31
    mare
    -0.31
    .',č↵
    -0.30
    POSITIVE LOGITS
     so
    0.32
    ,
    0.31
     continents
    0.28
     in
    0.26
    ´Ī
    0.25
    anguages
    0.25
     this
    0.25
    æīĢä»¥åľ¨
    0.24
     decision
    0.24
     thus
    0.24
    Activations Density 0.019%

    No Known Activations