© 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. 1988
    Prev
    Next
    INDEX
    Explanations

    prefixes like tra-, multi-, anti-, intra-, nano-

    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
    ORY
    -0.09
    rael
    -0.09
    ãģĦãģ¾ãģĻ
    -0.09
    -ie
    -0.09
    -fi
    -0.09
    бал
    -0.08
    æķ°æį®ä¸Ńå¿ĥ
    -0.08
    uet
    -0.08
    ×IJ׳×Ļ
    -0.08
    nt
    -0.08
    POSITIVE LOGITS
    ledger
    0.10
    ing
    0.09
    cept
    0.09
    ạm
    0.09
    ño
    0.09
    èĦ¾æ°Ķ
    0.08
    ä¸įåıĬ
    0.08
    akt
    0.08
    åľ¨éĤ£éĩĮ
    0.08
    atur
    0.08
    Activations Density 0.159%

    No Known Activations