© 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. 17282
    Prev
    Next
    INDEX
    Explanations

    names followed by last names

    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
    unte
    -0.09
    åĪ¶æľį
    -0.09
    å¾Īæĺ¯
    -0.09
    æĺ§
    -0.08
    çĿIJ
    -0.08
    AndView
    -0.08
    egr
    -0.08
    èĢ¨
    -0.08
    常è§Ħ
    -0.08
    åķĦ
    -0.08
    POSITIVE LOGITS
    è®®åijĺ
    0.10
    è®®æ¡Ī
    0.09
    代表
    0.09
    æ°ij主åħļ
    0.09
    为代表çļĦ
    0.09
    å½ĵéĢī
    0.09
    æ³½
    0.09
     депÑĥÑĤаÑĤ
    0.08
    à¸ŀรรà¸Ħ
    0.08
    ettle
    0.08
    Activations Density 0.096%

    No Known Activations