© 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. 31331
    Prev
    Next
    INDEX
    Explanations

    diagnose medical conditions

    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
    éĢ»
    -0.11
    antee
    -0.10
    ç»·
    -0.10
    bere
    -0.10
    å·«
    -0.09
    _ASM
    -0.09
    à¤Ŀ
    -0.09
    寸
    -0.09
    modifiable
    -0.09
     Forbes
    -0.09
    POSITIVE LOGITS
    èĢĺ
    0.11
    ä¸Ģ个éĹ®é¢ĺ
    0.10
    è´¶
    0.09
    mos
    0.08
    9
    0.08
    iat
    0.08
    iate
    0.08
    ละ
    0.08
    å¸ĪåħĦ
    0.08
    .Flat
    0.08
    Activations Density 0.003%

    No Known Activations