© 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. 62440
    Prev
    Next
    INDEX
    Explanations

    pigment

    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
    åIJĮä¸ļ
    -0.09
    irs
    -0.09
     одним
    -0.08
    è´±
    -0.08
    å¿įåıĹ
    -0.08
    éĢ®æįķ
    -0.08
    ç¾°
    -0.08
    apiro
    -0.08
    èĻIJå¾ħ
    -0.08
    æĮļ
    -0.08
    POSITIVE LOGITS
    èī²ç´ł
    0.12
    é¢ľ
    0.11
    èī³
    0.10
    墨
    0.10
    èī²å½©
    0.10
    pig
    0.10
    æĹ¶ä»£
    0.10
    åijĽ
    0.09
     pigment
    0.09
    çļĦé¢ľèī²
    0.09
    Activations Density 0.190%

    No Known Activations