© 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. 50873
    Prev
    Next
    INDEX
    Explanations

    Last names

    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
    ime
    -0.09
     завиÑģ
    -0.08
    ä»Ģ
    -0.08
    alan
    -0.08
    vez
    -0.08
    é¬ĥ
    -0.08
    alars
    -0.08
    halb
    -0.08
    èĤļ
    -0.08
    ä¸Ńåħ±ä¸Ń央
    -0.08
    POSITIVE LOGITS
    侯
    0.09
    æѤåĪ»
    0.09
    èĴº
    0.09
    æħµ
    0.09
     pari
    0.09
     Dillon
    0.09
    sert
    0.08
    åIJĮæŃ¥
    0.08
    leon
    0.08
    å¥Ń
    0.08
    Activations Density 0.002%

    No Known Activations