© 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. 19994
    Prev
    Next
    INDEX
    Explanations

    copper deficiency

    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
    妥
    -0.10
    ions
    -0.09
    оÑĢ
    -0.09
    平淡
    -0.09
    诮
    -0.09
    ç³Ĺ
    -0.09
    éĻħ
    -0.09
    olon
    -0.09
    orian
    -0.09
    ult
    -0.09
    POSITIVE LOGITS
    mith
    0.11
    æł·çļĦ
    0.11
    ä»Ģä¹ĪåİŁåĽł
    0.10
    nell
    0.09
    çľģå§Ķ
    0.09
    itore
    0.09
    -collar
    0.09
    wald
    0.09
    åĵĩ
    0.09
    æ±Ń
    0.08
    Activations Density 0.016%

    No Known Activations