© 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. 39657
    Prev
    Next
    INDEX
    Explanations

    transportation systems and infrastructure

    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¿
    -0.11
    itude
    -0.10
    zers
    -0.09
    æªĢ
    -0.09
    sWith
    -0.09
    hound
    -0.09
    пÑĢоÑģ
    -0.09
    åıĤè°ĭ
    -0.09
    worm
    -0.09
    иÑĦика
    -0.09
    POSITIVE LOGITS
    baugh
    0.11
    iglia
    0.08
    lect
    0.08
    .persistent
    0.08
    ught
    0.08
    fts
    0.08
    ono
    0.08
    ÑĢÑĥб
    0.08
    渺
    0.08
    lyph
    0.08
    Activations Density 0.010%

    No Known Activations