© 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. 19817
    Prev
    Next
    INDEX
    Explanations

    crop, clip, cut, trim, drop

    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
     Pompe
    -0.09
    éĴĪ
    -0.08
     concrete
    -0.08
    èµ°äºĨ
    -0.08
    appa
    -0.08
    ç§Ģ
    -0.08
    æµģåĬ¨
    -0.08
    åİŁè°ħ
    -0.08
    ksen
    -0.08
    è´¨
    -0.08
    POSITIVE LOGITS
     clipping
    0.12
    åīª
    0.11
    è£ģ
    0.10
    åĪĩéĻ¤
    0.10
    cut
    0.10
    两端
    0.10
    åĵij
    0.10
    åīĬ
    0.10
    ä¾ĽéľĢ
    0.10
    -cut
    0.09
    Activations Density 0.122%

    No Known Activations