© 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. 17074
    Prev
    Next
    INDEX
    Explanations

    beliefs and service

    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
    зон
    -0.11
    seealso
    -0.08
    eson
    -0.08
    onomy
    -0.08
    TTY
    -0.08
    icot
    -0.08
     اÙĦراب
    -0.08
    antz
    -0.08
    çĪ±æĬ¤
    -0.08
    æľįåĬ¡åĮº
    -0.08
    POSITIVE LOGITS
     Fal
    0.10
    éĺ²æ²»
    0.10
    èĪĽ
    0.09
    åİĺ
    0.09
    羣缸
    0.09
    íĺij
    0.09
    Fal
    0.09
    ç±¼
    0.09
    ç«ĭåľº
    0.09
    央ä¼ģ
    0.09
    Activations Density 0.057%

    No Known Activations