© 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. 38823
    Prev
    Next
    INDEX
    Explanations

    date and time

    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
    æľīæľº
    -0.10
    леж
    -0.10
    achs
    -0.10
    è°¤
    -0.10
    ç§ĭ天
    -0.09
    iston
    -0.09
    CCI
    -0.09
    PRI
    -0.09
    allis
    -0.09
    çIJ³
    -0.09
    POSITIVE LOGITS
     пÑĢоведениÑı
    0.10
    äºĨä¸Ģåľº
    0.09
     Gaut
    0.08
    ns
    0.08
    å±Ģéķ¿
    0.08
    inator
    0.08
    azine
    0.08
    WAY
    0.08
    åĿļ
    0.08
    å°±é¤IJ
    0.07
    Activations Density 0.040%

    No Known Activations