© 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. 53793
    Prev
    Next
    INDEX
    Explanations

    possibilities, opportunities, options

    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
    éĴ°
    -0.09
    çľ¼è§Ĵ
    -0.09
    åħ´èµ·
    -0.09
    WARE
    -0.09
    UGH
    -0.08
    ersed
    -0.08
    管çIJĨåĪ¶åº¦
    -0.08
    dap
    -0.08
    Ñįм
    -0.08
    æıIJèµ·
    -0.08
    POSITIVE LOGITS
     possibilities
    0.14
    åı¯èĥ½æĢ§
    0.11
    æĹłéĻIJ
    0.11
    æĹłæķ°
    0.10
    çļĦåı¯èĥ½æĢ§
    0.09
     possibilit
    0.09
    çļĦçIJĨçĶ±
    0.09
    åĢŁåı£
    0.09
    俯
    0.09
    poss
    0.09
    Activations Density 0.174%

    No Known Activations