© 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. 35464
    Prev
    Next
    INDEX
    Explanations

    explosive events 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
    åħ±åĴĮåĽ½
    -0.10
    resses
    -0.10
    west
    -0.09
    eras
    -0.09
     pragma
    -0.09
    estroy
    -0.09
    ivers
    -0.09
    esh
    -0.08
    ç»ŀ
    -0.08
    erk
    -0.08
    POSITIVE LOGITS
    ç½ķ
    0.12
    ÑĢÑĥд
    0.11
    ively
    0.11
    oter
    0.10
    licit
    0.10
    ions
    0.09
    tober
    0.09
    ä½Ĩä¸įéĻIJäºİ
    0.09
    ible
    0.09
    æĻ°
    0.09
    Activations Density 0.005%

    No Known Activations