© 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. 18060
    Prev
    Next
    INDEX
    Explanations

    questioning how to phrase things

    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
    orage
    -0.09
    å¿Ļ
    -0.09
    iento
    -0.09
    opes
    -0.09
    OCI
    -0.08
    å¿Ļç¢Į
    -0.08
    å±ĢéĿ¢
    -0.08
    çģ¯åħ·
    -0.08
    åĽ½ç±į
    -0.08
    çļĦå±ĢéĿ¢
    -0.08
    POSITIVE LOGITS
    è¿Ļ个è¯į
    0.11
    åıijéŁ³
    0.10
    äºĮåŃĹ
    0.09
    åIJ«ä¹ī
    0.09
    è¯įæ±ĩ
    0.09
    æ±īè¯Ń
    0.09
     rehabilit
    0.09
     sounding
    0.08
     tac
    0.08
    sheet
    0.08
    Activations Density 0.506%

    No Known Activations