© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 52930
    Prev
    Next
    INDEX
    Explanations

    hate and hateful expressions

    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
     tenth
    -0.09
    -animate
    -0.09
    OGLE
    -0.09
    æľĭ
    -0.08
    ä¸įèī¯
    -0.08
    åıijå±ķè§ĦåĪĴ
    -0.08
    ãģĨãģ¡ãģ«
    -0.08
    æĪijçľĭ
    -0.08
    inar
    -0.08
    erk
    -0.08
    POSITIVE LOGITS
    åĨ²éĶĭ
    0.11
    åĥįãģį
    0.09
    纡
    0.09
    fulness
    0.09
    ivi
    0.09
    沸èħ¾
    0.08
    Ñĥ
    0.08
    溢
    0.08
     Berm
    0.08
    iable
    0.08
    Activations Density 0.008%

    No Known Activations