© 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. 53138
    Prev
    Next
    INDEX
    Explanations

    ambitious plans and business

    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
    onym
    -0.09
    oine
    -0.09
    忧èĻij
    -0.08
    enstein
    -0.08
    utc
    -0.08
    ÙĪÙĩ
    -0.08
    aways
    -0.08
    arella
    -0.08
     omin
    -0.08
    ction
    -0.08
    POSITIVE LOGITS
    åĭĥåĭĥ
    0.18
    满满
    0.12
    assadors
    0.10
    满满çļĦ
    0.10
    éŃĦ
    0.09
    inus
    0.09
    éĺ¶å±Ĥ
    0.09
    _stdio
    0.09
    hek
    0.09
     má»ıi
    0.09
    Activations Density 0.005%

    No Known Activations