© 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. 32558
    Prev
    Next
    INDEX
    Explanations

    speed

    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
    ë¦Ħ
    -0.09
    hip
    -0.09
    ÑĪка
    -0.09
     lẽ
    -0.09
    £
    -0.09
    го
    -0.09
    æīĢ以说
    -0.08
    asure
    -0.08
     thirds
    -0.08
    媳
    -0.08
    POSITIVE LOGITS
    0.14
    idious
    0.12
    boat
    0.10
    ier
    0.10
    ily
    0.10
    lier
    0.10
    ened
    0.09
    骤
    0.09
    heets
    0.09
     Pública
    0.09
    Activations Density 0.039%

    No Known Activations