© 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. 50100
    Prev
    Next
    INDEX
    Explanations

    group, oria, cup, recover, ress, ab, atri

    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
    港åĮº
    -0.11
    ç½Ĥ
    -0.11
    леп
    -0.09
    CharacterSet
    -0.09
     kèm
    -0.09
    ToArray
    -0.09
    è´´
    -0.09
    æ»ĵ
    -0.09
    ÑģÑĮ
    -0.09
     tiếng
    -0.09
    POSITIVE LOGITS
    ä¸įåıĬ
    0.10
    ä¸įä½³
    0.09
    shine
    0.09
    eenth
    0.09
    ï¸
    0.09
    eração
    0.08
    æľīæķĪåľ°
    0.08
    ÎĻ
    0.08
    eking
    0.08
    éĻ¤éĿŀ
    0.08
    Activations Density 0.004%

    No Known Activations