© 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. 4462
    Prev
    Next
    INDEX
    Explanations

    pink

    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
    olest
    -0.09
    åĩĽ
    -0.09
     oily
    -0.09
    表æĥħ
    -0.09
    моÑĤ
    -0.09
    wend
    -0.08
    èĬĤæĹ¥
    -0.08
    èĦ¸èī²
    -0.08
    æ·Ŀ
    -0.08
     Ñĥзн
    -0.08
    POSITIVE LOGITS
    Pink
    0.12
     pink
    0.11
    pink
    0.11
     Pink
    0.10
     Blo
    0.10
    ç²īèī²
    0.09
    çıĬçijļ
    0.09
    å®ľå±ħ
    0.09
    .Typed
    0.09
    ä½ķ
    0.09
    Activations Density 0.029%

    No Known Activations