© 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. 32285
    Prev
    Next
    INDEX
    Explanations

    us cities

    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
    åĪ°æĿ¥
    -0.11
    çī©çIJĨåѦ
    -0.11
    èĮ«
    -0.10
    æĭĵ
    -0.10
    LD
    -0.10
    æ®ĭçķĻ
    -0.10
    ä¹ĭ家
    -0.10
    åĿŀ
    -0.09
    åĥ»
    -0.09
    åħµåĻ¨
    -0.09
    POSITIVE LOGITS
    oyo
    0.09
    rze
    0.08
     Abram
    0.08
    legg
    0.08
    åľĪ
    0.08
    æ¹¾åĮº
    0.08
     lance
    0.08
    çĽij
    0.08
    é¢Ĩ
    0.08
     qed
    0.08
    Activations Density 0.324%

    No Known Activations