© 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. 5279
    Prev
    Next
    INDEX
    Explanations

    concrete and its uses

    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
    åĶ®
    -0.09
    妫
    -0.08
    åħ¨åijĺ
    -0.08
    çŃļ
    -0.08
    ç»ıèIJ¥æ´»åĬ¨
    -0.08
    èĶĵ
    -0.08
    çĶŁæ´»çݯå¢ĥ
    -0.08
    å©ļ
    -0.08
    çݯå¢ĥåį«çĶŁ
    -0.08
    ä¿ĿéĻ©åħ¬åı¸
    -0.08
    POSITIVE LOGITS
    æµĩ
    0.11
     меÑĤÑĢо
    0.10
    ãĥŃãĥ³
    0.10
    éĴ¢çŃĭ
    0.09
    çł¼
    0.09
    åģĪ
    0.09
    è¤Ĭ
    0.09
    èĪ²
    0.08
    åĨ°åĨ·
    0.08
    uting
    0.08
    Activations Density 0.030%

    No Known Activations