© 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. 35365
    Prev
    Next
    INDEX
    Explanations

    cool, fresh, healthy, clean

    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¿Ļ让
    -0.09
    .cy
    -0.09
     ÑģкоÑĢо
    -0.08
    iffin
    -0.08
    ium
    -0.08
    afil
    -0.08
    çļĦ巨大
    -0.08
    inte
    -0.08
    çļĦé«ĺ度
    -0.08
    èĩªå¸¦
    -0.08
    POSITIVE LOGITS
    å¾ĭ
    0.10
    yal
    0.09
    ç¦ıç¥ī
    0.09
    æ´¥
    0.09
     Rounded
    0.08
    imas
    0.08
    RB
    0.08
    èĽĬ
    0.08
    brook
    0.08
    çĤľ
    0.08
    Activations Density 0.030%

    No Known Activations