© 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. 57978
    Prev
    Next
    INDEX
    Explanations

    Martin, Vidic, Monreal, Wieters

    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
    ç½²
    -0.10
    çĩĥæ²¹
    -0.10
    å²Ķ
    -0.10
    æµģçķħ
    -0.09
    åĢ¾
    -0.09
    访
    -0.09
    èĬ±æł·
    -0.09
    igaret
    -0.09
    unate
    -0.09
    .Relative
    -0.09
    POSITIVE LOGITS
    èݼ
    0.10
    å¤ļå¹´
    0.09
    orum
    0.09
    æµĬ
    0.09
    ä¸Ī
    0.09
    èĩªåĪ¶
    0.08
    森æŀĹ
    0.08
    åĿļå®ļä¸į移
    0.08
    é¾Ļæ¹ĸ
    0.08
    çī¢åĽº
    0.08
    Activations Density 0.044%

    No Known Activations