© 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. 32058
    Prev
    Next
    INDEX
    Explanations

    our + noun phrase

    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
    èĦijåŃIJéĩĮ
    -0.09
    зо
    -0.09
    oser
    -0.09
    åŃĢ
    -0.09
    åĪ·æĸ°
    -0.09
    ç»Ń
    -0.08
    èĢĮéĿŀ
    -0.08
    enders
    -0.08
    èķĻ
    -0.08
    æĺİåªļ
    -0.08
    POSITIVE LOGITS
    msgid
    0.09
    å¹´æĬ¥
    0.08
     WrocÅĤaw
    0.08
    è¿IJä½ľ
    0.08
    _GB
    0.08
    åħ¨æĹ¥
    0.08
    éĺĻ
    0.08
    åŀĤ
    0.08
    CI
    0.08
     gest
    0.08
    Activations Density 0.057%

    No Known Activations