© 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. 19459
    Prev
    Next
    INDEX
    Explanations

    rc groups, RC versions, rcamera

    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
    庶
    -0.08
    åŀł
    -0.08
    .setCharacter
    -0.08
    ÑĢоз
    -0.08
    ungan
    -0.08
    inati
    -0.08
    баÑĢ
    -0.08
    综åIJĪ
    -0.08
    -faced
    -0.08
     aforementioned
    -0.08
    POSITIVE LOGITS
    èĪ±
    0.10
    eer
    0.09
    çķħéĢļ
    0.09
    ãģĤãģ£ãģ¦
    0.09
    æłī
    0.09
    ytt
    0.08
    orsi
    0.08
     diss
    0.08
    åIJİ代
    0.08
    aan
    0.08
    Activations Density 0.034%

    No Known Activations