© 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. 31065
    Prev
    Next
    INDEX
    Explanations

    concise description

    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
    ige
    -0.10
    浪
    -0.10
    iran
    -0.09
    éĢĨè¡Į
    -0.09
    urge
    -0.09
    irk
    -0.09
    tim
    -0.09
    stä
    -0.09
    åľ¨äº¬
    -0.08
    quate
    -0.08
    POSITIVE LOGITS
    ç®Ģæ´ģ
    0.17
     gá»įn
    0.16
    ç®Ģ
    0.12
    æī¼
    0.12
    ç®Ģ约
    0.11
    èĤ¯
    0.11
    ç´§åĩij
    0.10
    çŃĴ
    0.10
    /plain
    0.10
     bre
    0.10
    Activations Density 0.032%

    No Known Activations