© 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. 6500
    Prev
    Next
    INDEX
    Explanations

    sensor

    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
    elas
    -0.09
    erten
    -0.08
    ensions
    -0.08
    ibrator
    -0.08
    аÑĪ
    -0.08
    nut
    -0.08
    å¢ŀè¿Ľ
    -0.08
    odus
    -0.08
    coat
    -0.08
    erm
    -0.08
    POSITIVE LOGITS
    инг
    0.10
    ially
    0.10
    ç¿°
    0.10
    åĸŁ
    0.10
    æİ¢
    0.09
    ิà¸ģ
    0.09
    RECT
    0.09
    encer
    0.09
    aggio
    0.08
    ial
    0.08
    Activations Density 0.068%

    No Known Activations