© 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. 48914
    Prev
    Next
    INDEX
    Explanations

    Hall of Fame

    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
    é¢ĦåijĬ
    -0.10
    .rad
    -0.09
    æĶ¿åºľéĩĩè´Ń
    -0.09
    女è£ħ
    -0.08
    finder
    -0.08
    éĻħ
    -0.08
    绣
    -0.08
    èĹĵ
    -0.08
    monkey
    -0.08
    ãģĺ
    -0.08
    POSITIVE LOGITS
    èĢģ
    0.11
    /goto
    0.10
    èĢģåĮĸ
    0.10
    寿
    0.10
    åľ°åĿĹ
    0.09
    isco
    0.09
    æŀ¶åŃIJ
    0.09
     ÑģÑĤаÑĢ
    0.09
    thora
    0.09
    çºłæŃ£
    0.09
    Activations Density 0.229%

    No Known Activations