© 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. 27384
    Prev
    Next
    INDEX
    Explanations

    nicknames or aliases

    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
    èݲèĬ±
    -0.10
    è±³
    -0.09
    çŁį
    -0.08
     strike
    -0.08
    糯米
    -0.08
    æ°´åĪĨ
    -0.08
    河西
    -0.08
    otropic
    -0.08
    æľ´
    -0.08
    ç»ŀ
    -0.08
    POSITIVE LOGITS
     Repo
    0.09
    repo
    0.09
    ä¹ĭç¾İ
    0.09
    èĦĨ
    0.09
    çĶ·åŃ©
    0.09
    ãĤ³ãĥ¬
    0.09
     orang
    0.08
     мом
    0.08
    ä½łçľĭ
    0.08
    å§Ķ
    0.08
    Activations Density 0.121%

    No Known Activations