© 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. 49844
    Prev
    Next
    INDEX
    Explanations

    describes or description

    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
    è°·
    -0.09
    åIJĦå¼ı
    -0.09
    çĦ¦
    -0.09
     scre
    -0.09
    çļĦæľĢ大
    -0.08
    åģļ好
    -0.08
    å½Ń
    -0.08
     Murray
    -0.08
    veau
    -0.08
    orate
    -0.08
    POSITIVE LOGITS
    OTH
    0.10
    å®īéĺ²
    0.09
    ROTO
    0.09
    çļ®èĤ¤çĹħ
    0.09
    äºĨä»ĸçļĦ
    0.09
    å±±åºĦ
    0.09
    çķĮçļĦ
    0.09
    详ç»Ĩ
    0.09
    è´§çī©
    0.09
    羣æĥħ
    0.09
    Activations Density 0.120%

    No Known Activations