© 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. 34486
    Prev
    Next
    INDEX
    Explanations

    avalanche or Avalon

    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
    zeitig
    -0.10
    ann
    -0.09
    ads
    -0.09
    overs
    -0.08
    ycle
    -0.08
    ening
    -0.08
    寤
    -0.08
    activ
    -0.08
    ened
    -0.08
    对ä¸įèµ·
    -0.08
    POSITIVE LOGITS
    0.10
    meer
    0.09
    åį³å°ĨåĪ°æĿ¥
    0.09
    owed
    0.09
    éļĻ
    0.09
    èĩªåľ¨
    0.09
    åı¯æĥ³
    0.09
    çĶŁçī©ç§ijæĬĢ
    0.09
    èĩ¬
    0.09
    ments
    0.09
    Activations Density 0.003%

    No Known Activations