© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 51619
    Prev
    Next
    INDEX
    Explanations

    linebacker or lineWidth

    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
    pliant
    -0.11
    ÑıÑī
    -0.10
    pecially
    -0.10
    馥
    -0.09
    une
    -0.09
    icular
    -0.09
    KHR
    -0.09
    ##_
    -0.08
    .Documents
    -0.08
    ICS
    -0.08
    POSITIVE LOGITS
    ness
    0.09
    DrawerToggle
    0.09
    etch
    0.08
    è·¯èĻİ
    0.08
    upo
    0.08
    enia
    0.08
    ãĥŃãĥ¼
    0.08
    太太
    0.08
     Straw
    0.08
    è´¨éĩıå®īåħ¨
    0.08
    Activations Density 0.003%

    No Known Activations