© 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. 6593
    Prev
    Next
    INDEX
    Explanations

    UI elements and data types

    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
    ä¹İ
    -0.14
    åĮĸè¿Ľç¨ĭ
    -0.11
    acky
    -0.10
    æŀī
    -0.10
    åľºä¸Ĭ
    -0.09
    wort
    -0.09
    çĪ·
    -0.09
     Jad
    -0.09
    åŃ½
    -0.09
    деÑģÑıÑĤ
    -0.09
    POSITIVE LOGITS
    ers
    0.13
    涯
    0.12
    sWith
    0.12
    ed
    0.10
    ÑĤÑĥ
    0.09
    iendo
    0.09
    edian
    0.09
    ting
    0.08
    ening
    0.08
    ym
    0.08
    Activations Density 0.970%

    No Known Activations