© 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. 7380
    Prev
    Next
    INDEX
    Explanations

    myspace, Bebo, plus

    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
    ãģ£ãģ±
    -0.11
    èķĪ
    -0.09
    Ñİ
    -0.08
     Citizens
    -0.08
    ior
    -0.08
    çıł
    -0.08
    å¸Ĥæ°ij
    -0.08
    ä¸ĸ人
    -0.08
    央è§Ĩ
    -0.08
    agu
    -0.08
    POSITIVE LOGITS
    benh
    0.09
    èĻij
    0.09
    çĸ¹
    0.09
    ç¬Ĩ
    0.09
    ified
    0.09
    è·Ľ
    0.09
    instr
    0.08
    æĿµ
    0.08
    èł¢
    0.08
    ron
    0.08
    Activations Density 0.003%

    No Known Activations