© 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. 54323
    Prev
    Next
    INDEX
    Explanations

    parts and conditions

    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
    åĩłçĤ¹
    -0.10
    ä¾¿å®ľ
    -0.09
    èĻ¹
    -0.09
    toolbox
    -0.09
     Pru
    -0.09
    msp
    -0.08
    ê²ł
    -0.08
    committee
    -0.08
    ç¥ī
    -0.08
     Imp
    -0.08
    POSITIVE LOGITS
    ä¿Ŀä¿®
    0.10
    èĩªè¡Į
    0.09
    å¹´éĻIJ
    0.09
    è¹ĩ
    0.09
    ÑĢаÐ
    0.09
     гаÑĢанÑĤи
    0.08
    人为
    0.08
    é¦ĸåħĪ
    0.08
    使çĶ¨èĢħ
    0.08
     Coaching
    0.08
    Activations Density 0.013%

    No Known Activations