© 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. 51171
    Prev
    Next
    INDEX
    Explanations

    places and landmarks

    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
    个åĪ«
    -0.09
    åĴ¸
    -0.09
    åĩºå·®
    -0.09
    快讯
    -0.08
    家åĬ¡
    -0.08
    æIJŃ
    -0.08
    åĴ«
    -0.08
    aines
    -0.08
    vere
    -0.08
    æĿµ
    -0.08
    POSITIVE LOGITS
    åħįç¨İ
    0.10
    å°ıæľĭåıĭ
    0.10
    ç¾İæľ¯é¦Ĩ
    0.09
    庾
    0.09
    表
    0.08
    è¿ģ
    0.08
     Ñĥзн
    0.08
    éĹ®é¢ĺæĺ¯
    0.08
     hands
    0.08
    åįļçī©é¦Ĩ
    0.08
    Activations Density 0.207%

    No Known Activations