© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 36014
    Prev
    Next
    INDEX
    Explanations

    shows impressive, which seems, we are

    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
    é¥ķ
    -0.08
    åıĻ
    -0.08
    noinspection
    -0.07
    æĪijå½ĵæŶ
    -0.07
    .nc
    -0.07
    SPA
    -0.07
    æĪij个人
    -0.07
    éģĦ
    -0.07
    èŤ
    -0.07
    ilon
    -0.07
    POSITIVE LOGITS
    пÑĢе
    0.10
    éĩį温
    0.09
    èĩªæľī
    0.09
    æį·
    0.09
    idot
    0.09
    ItemAt
    0.09
    luent
    0.09
    åĨµä¸Ķ
    0.09
    带éĺŁ
    0.09
    æ²¹æ°Ķ
    0.09
    Activations Density 0.062%

    No Known Activations