© 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. 11437
    Prev
    Next
    INDEX
    Explanations

    glimpse

    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
    æħ¢æħ¢åľ°
    -0.10
     пÑĢим
    -0.10
     Gree
    -0.09
    ance
    -0.09
    à¹Ħà¸Ĺย
    -0.09
    OWN
    -0.09
    dit
    -0.09
    wards
    -0.08
    ally
    -0.08
    rop
    -0.08
    POSITIVE LOGITS
    çªĹå¤ĸ
    0.12
    æĽĻåħī
    0.11
    åķĨæľº
    0.10
    еÑĤÑĮ
    0.10
    atch
    0.10
    yü
    0.10
    åŃIJéĩĮ
    0.09
    踪
    0.09
    edian
    0.09
    wis
    0.09
    Activations Density 0.006%

    No Known Activations