© 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. 10011
    Prev
    Next
    INDEX
    Explanations

    prey and mammals

    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
    åIJ¸
    -0.10
    衾
    -0.10
    çģŃçģ«
    -0.09
    ä¸įåŃĺåľ¨
    -0.08
    _BUCKET
    -0.08
    èĤĩ
    -0.08
    auth
    -0.08
    çĭ±
    -0.08
    xFD
    -0.08
    .obtain
    -0.08
    POSITIVE LOGITS
    鹿
    0.09
     deer
    0.09
    é¢Ĥ
    0.08
    æłĿ
    0.08
    ière
    0.08
    å°±å¾Ī
    0.08
     populations
    0.08
    çĽ¥
    0.08
    inner
    0.08
    isArray
    0.08
    Activations Density 0.049%

    No Known Activations