© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 59148
    Prev
    Next
    INDEX
    Explanations

    IT, software, Oracle, requirements

    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
    ä¿¡æģ¯æľįåĬ¡
    -0.08
    arte
    -0.08
    achi
    -0.08
    çľĭä¸įæĩĤ
    -0.08
    Interpreter
    -0.08
    éģĵå¾·
    -0.08
    å®ļçĤ¹
    -0.08
    tor
    -0.08
     rejected
    -0.07
    éĢĴç»Ļ
    -0.07
    POSITIVE LOGITS
    秽
    0.09
    ä»İä¸ļ
    0.09
     phé
    0.09
    .crm
    0.09
    umper
    0.08
    ä¸¤åľ°
    0.08
    ä¸ĢåĪĻ
    0.08
    .office
    0.08
     forensic
    0.08
     nug
    0.08
    Activations Density 1.051%

    No Known Activations