© 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. 39850
    Prev
    Next
    INDEX
    Explanations

    growing population

    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
    æĿŁ
    -0.13
    祺
    -0.10
    åıįèħIJåĢ¡å»ī
    -0.10
    åı¯çĸij
    -0.10
     Impl
    -0.10
    _chi
    -0.10
    urve
    -0.10
    åľºä¸Ĭ
    -0.09
    å½ĵéĢī
    -0.09
    ä¸įéĻIJ
    -0.09
    POSITIVE LOGITS
    人åı£
    0.16
    æĪ·ç±į
    0.12
     population
    0.12
     populations
    0.11
    population
    0.11
     demographic
    0.10
    å±ħä½ı
    0.10
    Population
    0.09
    移æ°ij
    0.09
    æµģ失
    0.09
    Activations Density 0.084%

    No Known Activations