© 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. 57258
    Prev
    Next
    INDEX
    Explanations

    motor vehicle and cycles

    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
    æİ®
    -0.09
    adow
    -0.08
     Blond
    -0.08
    nor
    -0.08
     {.
    -0.08
    /Page
    -0.08
    æĭĶ
    -0.08
    adero
    -0.08
    çľ¼éĩĮ
    -0.08
    æĿ²
    -0.08
    POSITIVE LOGITS
    ized
    0.14
    ised
    0.11
    ization
    0.11
    åĮĸçļĦ
    0.11
    izable
    0.11
    isation
    0.10
    less
    0.10
    åıijå±ķéĺ¶æ®µ
    0.10
    ted
    0.09
    line
    0.09
    Activations Density 0.017%

    No Known Activations