© 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. 39068
    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_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
     cará
    -0.31
    åĨįåİ»
    -0.27
    .space
    -0.26
    /bower
    -0.24
    ito
    -0.24
    åĪ¶æŃ¢
    -0.24
    å·²ç»ıæľī
    -0.24
    EdgeInsets
    -0.24
    och
    -0.23
    Above
    -0.23
    POSITIVE LOGITS
    æĭĶ
    0.29
    æı´
    0.26
    æĭħ
    0.25
     reim
    0.25
    è¯ļ
    0.24
     Minor
    0.24
    inish
    0.24
    ãģĭãģĭãĤĭ
    0.24
    erry
    0.24
     affiliated
    0.24
    Activations Density 37.637%

    No Known Activations