© 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. 57259
    Prev
    Next
    INDEX
    Explanations

    black

    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
    åįĹåĮĹ
    -0.09
    羣æŃ£
    -0.09
    羣æŃ£çļĦ
    -0.08
     ка
    -0.08
    -IN
    -0.08
    orsi
    -0.08
     Clippers
    -0.08
    ement
    -0.08
    æ°Ķ象
    -0.08
    orthand
    -0.08
    POSITIVE LOGITS
    /black
    0.16
    -black
    0.15
    black
    0.13
    é»ij
    0.13
    Black
    0.13
    é»ijèī²
    0.12
     BLACK
    0.12
    BLACK
    0.12
     Black
    0.12
    .black
    0.11
    Activations Density 0.092%

    No Known Activations