© 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. 51035
    Prev
    Next
    INDEX
    Explanations

    Brooklyn

    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
    leine
    -0.10
    ç§Ģ丽
    -0.09
     Lod
    -0.09
    ãĤĤãĤĬ
    -0.09
    è¿Ľåľº
    -0.09
    èľ¡
    -0.09
    eya
    -0.09
    åĿŁ
    -0.09
    омеÑĢ
    -0.09
    太é«ĺ
    -0.09
    POSITIVE LOGITS
    PIPE
    0.09
    aise
    0.09
    adel
    0.09
    æĭ£
    0.09
    rs
    0.08
    å°±åĮ»
    0.08
    RS
    0.08
    ç¦ħ
    0.08
    éĩį度
    0.08
    ometer
    0.08
    Activations Density 0.007%

    No Known Activations