© 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. 5319
    Prev
    Next
    INDEX
    Explanations

    music related content

    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
    alin
    -0.10
    oute
    -0.09
    Ñģен
    -0.09
    ç©Ĺ
    -0.08
    INGER
    -0.08
    çļĦ姿æĢģ
    -0.08
     Germ
    -0.08
    æ¨¡æł·
    -0.08
    åħ¬è·¯
    -0.08
     replay
    -0.08
    POSITIVE LOGITS
    èı©
    0.10
    .createObject
    0.09
    adders
    0.08
    æĥ®
    0.08
    oven
    0.08
    Dup
    0.08
    çĶ»çĶ»
    0.08
    apiro
    0.08
    Ậ
    0.08
    áºŃt
    0.08
    Activations Density 0.036%

    No Known Activations