© 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
    2. Qwen3-32B
    3. 32-RESID-BATCHTOPK-65K
    4. 53652
    Prev
    Next
    INDEX
    Explanations

    collection and material

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-32b-saes/saes_Qwen_Qwen3-32B_batch_top_k/resid_post_layer_32
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    è¯ij
    -0.09
    laps
    -0.09
    ataires
    -0.09
    é¥ķ
    -0.09
    åīľ
    -0.09
    OPSIS
    -0.09
    æĪIJçĨŁ
    -0.09
    pure
    -0.09
    åijĬ
    -0.08
    å®´
    -0.08
    POSITIVE LOGITS
    åŀĽ
    0.10
    è¹¼
    0.10
    å¹³åĿĩ
    0.09
    ä¸Ńå¿ĥ主任
    0.09
    @endforeach
    0.09
    Center
    0.09
    å¯Įæľī
    0.09
    Snap
    0.09
    cope
    0.09
    ä¸Ńå¿ĥ
    0.08
    Activations Density 0.089%

    No Known Activations