© 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. 10076
    Prev
    Next
    INDEX
    Explanations

    tablespoon, tsp, or tablespace

    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
    ouce
    -0.11
    otta
    -0.11
    å°ıåŃIJ
    -0.10
    rink
    -0.10
    lsen
    -0.10
    ள
    -0.10
     ì²ĺ
    -0.10
    åİ»åĮ»éĻ¢
    -0.09
    бÑĢоÑģ
    -0.09
    OUNCE
    -0.09
    POSITIVE LOGITS
    ionate
    0.09
    eller
    0.09
    åħ³éŨ
    0.09
    n
    0.08
    ELL
    0.08
    ellant
    0.08
    аÑĪ
    0.08
    alt
    0.07
    ds
    0.07
    说æĺ¯
    0.07
    Activations Density 0.002%

    No Known Activations