© 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. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 54427
    Prev
    Next
    INDEX
    Explanations

    pass variations

    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
    à¸Ľà¸ģà¸Ħรà¸Ńà¸ĩ
    -0.09
    æ·±æ·±åľ°
    -0.09
    orrent
    -0.09
    jej
    -0.09
    arest
    -0.09
    å»ĵ
    -0.09
    éĺĶ
    -0.09
    åħ¶æ¬¡æĺ¯
    -0.09
    éĿ¢è²Į
    -0.09
    anks
    -0.09
    POSITIVE LOGITS
    engers
    0.11
    (pass
    0.11
    ively
    0.11
     pass
    0.10
    /pass
    0.10
    enger
    0.10
    pass
    0.10
    ions
    0.09
    æĸ
    0.09
    çľĭçĿĢ
    0.09
    Activations Density 0.023%

    No Known Activations