© 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. 1879
    Prev
    Next
    INDEX
    Explanations

    longer, not, exactly

    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
    éĢļãĤĬ
    -0.09
    leans
    -0.08
    виÑĤ
    -0.08
    .pat
    -0.08
    éĹ®éĹ®
    -0.08
     Carrier
    -0.08
    è·
    -0.08
    ounty
    -0.07
    çĥľ
    -0.07
    asaki
    -0.07
    POSITIVE LOGITS
    æĬij
    0.09
    åĪĽä¼¤
    0.08
    _maximum
    0.08
    èĦ©
    0.08
    ä¿®
    0.08
    åĽŀåij³
    0.08
    oke
    0.08
    çĪ±å¥½
    0.08
    å¼Ģæ°´
    0.08
    conto
    0.08
    Activations Density 0.566%

    No Known Activations