© 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. 38963
    Prev
    Next
    INDEX
    Explanations

    v

    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
    rant
    -0.26
    æ£Ĵ
    -0.25
     Stamp
    -0.24
    머
    -0.23
    ê²°
    -0.23
    å°
    -0.23
    ores
    -0.23
     Chr
    -0.23
    æĵįä½ľ
    -0.23
    à¸Ńาย
    -0.23
    POSITIVE LOGITS
    its
    0.30
    ä½Ĩä»ĸ
    0.29
    .apps
    0.28
    aab
    0.28
    çİ°å®ŀ
    0.28
    isko
    0.28
    ä½Ĩæĺ¯ä»ĸ
    0.27
    ainty
    0.27
    ual
    0.27
    wald
    0.27
    Activations Density 2.006%

    No Known Activations