© 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. 18285
    Prev
    Next
    INDEX
    Explanations

    ``````

    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
    aida
    -0.10
    ä¸ľè¥¿
    -0.09
    hue
    -0.09
    ORIZED
    -0.08
    ugu
    -0.08
    viso
    -0.08
    书æ³ķ家
    -0.08
    olest
    -0.08
    Nib
    -0.08
    å°¼æĸ¯
    -0.08
    POSITIVE LOGITS
    éªļ
    0.09
    ãģ¤ãģĭ
    0.09
    车è¾Ĩ
    0.08
    èħ¿éĥ¨
    0.08
     TEM
    0.08
    acre
    0.08
    dv
    0.08
    èĤ¼
    0.08
    Fullscreen
    0.08
     desi
    0.08
    Activations Density 0.008%

    No Known Activations