© 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. 30696
    Prev
    Next
    INDEX
    Explanations

    ISBNs and other identifiers with delimiters

    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
    è§ĩ
    -0.12
    æ®ĸ
    -0.10
     Pry
    -0.10
    æ¯ģ
    -0.10
    PIO
    -0.09
    realm
    -0.09
    çĿ¥
    -0.09
    clide
    -0.09
    phia
    -0.09
    ç§ijæķĻ
    -0.09
    POSITIVE LOGITS
    alus
    0.09
    èŀºæĹĭ
    0.09
     pa
    0.08
     ped
    0.08
    yb
    0.08
    annot
    0.08
     Handler
    0.07
    bolt
    0.07
    lover
    0.07
     unk
    0.07
    Activations Density 0.016%

    No Known Activations