© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 50427
    Prev
    Next
    INDEX
    Explanations

    free agents

    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
     пока
    -0.10
    oub
    -0.09
    å½ķçĶ¨
    -0.09
    æķĻèĤ²æķĻåѦ
    -0.09
     feudal
    -0.09
    åıijèĤ²
    -0.08
    hest
    -0.08
    天èµĭ
    -0.08
    arium
    -0.08
    OUGH
    -0.08
    POSITIVE LOGITS
    afen
    0.09
    æ³¢çī¹
    0.09
    .inflate
    0.09
    宾é¦Ĩ
    0.08
    ç¿»å¼Ģ
    0.08
    æľĪåĪĿ
    0.08
    atee
    0.08
    åĴ¨è¯¢
    0.08
    çł´äº§
    0.08
    å§ĭç»Īä¿ĿæĮģ
    0.08
    Activations Density 0.014%

    No Known Activations