© 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. 58738
    Prev
    Next
    INDEX
    Explanations

    Watch, see, click, more

    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
    åĽłä¸ºæĪij
    -0.10
    æĪijå¦Ī
    -0.10
    éĶ¥
    -0.09
    åŀĤ
    -0.09
     Sparks
    -0.08
    讪
    -0.08
    ipt
    -0.08
    òng
    -0.08
    acr
    -0.08
    å¾Īæ£Ĵ
    -0.08
    POSITIVE LOGITS
    åħ·ä½ĵæĥħåĨµ
    0.09
    ç¦ıåĪ©
    0.09
    æĻļéĹ´
    0.09
    羡
    0.08
    涨价
    0.08
    çļĭ
    0.08
    çŁ¥æĥħ
    0.08
    对æѤ
    0.08
    rack
    0.08
    çĸijä¼¼
    0.08
    Activations Density 0.032%

    No Known Activations