© 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. 54041
    Prev
    Next
    INDEX
    Explanations

    Cait, AIT, kait

    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
    æĺ¯éŁ©åĽ½
    -0.11
    eur
    -0.11
    á»ĵi
    -0.10
    enk
    -0.09
    累累
    -0.09
    èĹľ
    -0.09
    çļĦåĸľçĪ±
    -0.09
    fleet
    -0.09
    奶奶
    -0.09
    èļ¬
    -0.08
    POSITIVE LOGITS
    ness
    0.13
    ting
    0.12
    rogen
    0.11
    TING
    0.09
    ALS
    0.09
    çĦ¶æĺ¯
    0.09
     Fran
    0.09
    讹
    0.08
    ement
    0.08
    rix
    0.08
    Activations Density 0.011%

    No Known Activations