© 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. 61045
    Prev
    Next
    INDEX
    Explanations

    devices including computers

    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
    agon
    -0.10
    è²Į
    -0.10
    ort
    -0.10
    abouts
    -0.09
    oma
    -0.09
    sters
    -0.09
    ener
    -0.09
     пÑĢеп
    -0.09
    cribe
    -0.09
    磬
    -0.08
    POSITIVE LOGITS
    ized
    0.12
    -readable
    0.10
    åľ¨è¿ĩ渡
    0.09
    azzi
    0.09
    Browsable
    0.09
    寮
    0.09
    ä¸į认è¯Ĩ
    0.09
    æµĨ
    0.08
    dos
    0.08
    åĽłä¸ºå®ĥ
    0.08
    Activations Density 0.052%

    No Known Activations