© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 8304
    Prev
    Next
    INDEX
    Explanations

    vision loss or problems

    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
    stance
    -0.09
    stands
    -0.09
    ãģĦãģij
    -0.09
    æľĪä¸ĭ
    -0.09
    sta
    -0.09
    ä¸Ģç«Ļ
    -0.08
    缦
    -0.08
    ew
    -0.08
    ç«ĻçĿĢ
    -0.08
    身å¤Ħ
    -0.08
    POSITIVE LOGITS
    æ¯ķ
    0.12
    еÑĤÑĮ
    0.11
    seeing
    0.10
    讫
    0.10
    ibilit
    0.09
    ðŁijĢ
    0.09
    aries
    0.09
    иÑĢÑĥ
    0.09
    尽头
    0.09
    frog
    0.09
    Activations Density 0.036%

    No Known Activations