© 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. 19250
    Prev
    Next
    INDEX
    Explanations

    hip-hop

    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
    丰ç¡ķ
    -0.10
    ÑģÑĤÑĥп
    -0.09
    기ê°Ģ
    -0.09
    EPS
    -0.08
    ance
    -0.08
    ÑĢÑĥд
    -0.08
     Cummings
    -0.08
    æĹĹå¸ľ
    -0.08
    æĢĢçĿĢ
    -0.08
    xin
    -0.08
    POSITIVE LOGITS
    ster
    0.13
    sters
    0.11
    STER
    0.11
    -hop
    0.10
    otle
    0.10
    ourg
    0.09
    erals
    0.09
    ness
    0.09
    licity
    0.09
    çİ©æĦı
    0.09
    Activations Density 0.009%

    No Known Activations