© 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. 53666
    Prev
    Next
    INDEX
    Explanations

    biography

    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
    ण
    -0.10
    atori
    -0.09
    anut
    -0.09
    Æ°u
    -0.09
    çŃł
    -0.09
    neo
    -0.08
    ivos
    -0.08
    ourn
    -0.08
    ager
    -0.08
    aber
    -0.08
    POSITIVE LOGITS
    æĶ¶å½ķ
    0.09
    opsis
    0.09
    оÑĢ
    0.09
    åĭĥåĭĥ
    0.09
    illion
    0.09
    ÃĵN
    0.08
    elong
    0.08
    å·¥ä½ľèĢħ
    0.08
    pped
    0.08
    olum
    0.08
    Activations Density 0.074%

    No Known Activations