© 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. 30639
    Prev
    Next
    INDEX
    Explanations

    host or hosting"}

    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
    请大家
    -0.10
    autop
    -0.10
    istan
    -0.09
    ixer
    -0.09
    aden
    -0.09
    éĢĶ
    -0.09
    ssi
    -0.08
    д
    -0.08
    AUT
    -0.08
    ony
    -0.08
    POSITIVE LOGITS
    ilities
    0.13
    ility
    0.10
    esses
    0.09
     же
    0.09
    ains
    0.09
    ITOR
    0.09
    fires
    0.09
    ess
    0.09
    çļĦä¸ĢåĪĩ
    0.09
    سÙĪ
    0.09
    Activations Density 0.021%

    No Known Activations