© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 52728
    Prev
    Next
    INDEX
    Explanations

    quick and easy preparation

    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
    丰满
    -0.09
    подоб
    -0.09
    èݹ
    -0.09
    åģ¥åħ¨
    -0.09
    orp
    -0.09
    äºİæĺ¯æĪij
    -0.08
     Osw
    -0.08
    acle
    -0.08
    мол
    -0.08
    å¾Ģå¹´
    -0.08
    POSITIVE LOGITS
    å¿«æį·
    0.10
    å¿«éĢŁ
    0.09
    ç®Ģ便
    0.09
    å¿«æīĭ
    0.09
    åºŁçī©
    0.09
    åĶ§
    0.09
    åĩłæŃ¥
    0.08
    顾
    0.08
    POSE
    0.08
    解æĶ¾
    0.08
    Activations Density 0.043%

    No Known Activations