© 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. 56124
    Prev
    Next
    INDEX
    Explanations

    universities and sports teams

    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
    mach
    -0.10
     админиÑģÑĤÑĢа
    -0.09
    天ä¸Ĭ
    -0.09
    使人
    -0.08
    mez
    -0.08
    åħ¨æĿij
    -0.08
    TeV
    -0.08
    IGNORE
    -0.08
    æĹģ
    -0.08
    itchens
    -0.08
    POSITIVE LOGITS
    åķĨåѦéĻ¢
    0.11
     adına
    0.10
    建çŃijå·¥ç¨ĭ
    0.10
    æĸ°åĨłçĸ«æĥħ
    0.09
    åIJĮç±»
    0.09
    åİĨåı²ä¸Ĭ
    0.09
    íķŃ
    0.09
    建çŃij
    0.09
    .fa
    0.09
    çĪ±å°Ķ
    0.09
    Activations Density 0.033%

    No Known Activations