© 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. 54812
    Prev
    Next
    INDEX
    Explanations

    .bi extension

    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
    اظ
    -0.08
     اÙĦخاÙħ
    -0.08
    Ùħست
    -0.08
    ĥĿ
    -0.08
    sson
    -0.08
    ([^
    -0.07
     Carlos
    -0.07
    acht
    -0.07
    ong
    -0.07
    ienen
    -0.07
    POSITIVE LOGITS
    åī¯ä¸»ä»»
    0.11
    pus
    0.10
    黳
    0.10
    åĸľæ¬¢åIJĥ
    0.10
     Gladiator
    0.09
    apult
    0.09
    ä»ĸå¦Ī
    0.09
    ÑĢай
    0.09
     ########.
    0.09
    å¸ĮæľĽèĩªå·±
    0.09
    Activations Density 0.460%

    No Known Activations