© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 32-TRANSCODER-HP
    7. 44048
    Prev
    Next
    INDEX
    Explanations

    1

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_32.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.32.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    __;
    -0.46
    _;
    -0.45
    ;',
    -0.38
    _;↵
    -0.35
    __',
    -0.34
     "";
    -0.34
    ];
    -0.34
    ;,
    -0.33
    ;",
    -0.33
    >;
    -0.33
    POSITIVE LOGITS
    )
    0.36
    )↵
    0.32
    —in
    0.30
    )↵↵
    0.29
     )↵
    0.29
    )m
    0.29
    —from
    0.29
    --)↵
    0.27
    —not
    0.27
     )↵↵
    0.27
    Activations Density 0.004%

    No Known Activations