© 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. 57471
    Prev
    Next
    INDEX
    Explanations

    fundraising and campaigns

    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
     subs
    -0.09
    åĪ»
    -0.08
    esk
    -0.08
    å¤ĩæ¡Ī
    -0.08
    æĿĥ
    -0.08
    å·¥èīº
    -0.08
    çŀĴ
    -0.08
     OCC
    -0.08
    ritable
    -0.08
    æ¢ĵ
    -0.08
    POSITIVE LOGITS
    éĺħ
    0.10
    ç®ķ
    0.10
    lamp
    0.09
    à¸Ħม
    0.09
    åįĪé¥Ń
    0.09
     campaign
    0.09
    COORD
    0.09
    aco
    0.09
    çļĦæľĢåIJİä¸Ģ
    0.09
    ãĤŃãĥ£ãĥ³ãĥļãĥ¼ãĥ³
    0.09
    Activations Density 0.178%

    No Known Activations