© 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. 56117
    Prev
    Next
    INDEX
    Explanations

    numbers and units after punctuation

    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
    _ci
    -0.09
    é£ŀæī¬
    -0.08
     baÅŁÄ±na
    -0.08
    agne
    -0.07
    æĭĴ
    -0.07
    幡
    -0.07
    _IDENT
    -0.07
    lsen
    -0.07
    essler
    -0.07
    eness
    -0.07
    POSITIVE LOGITS
    èĪĨ
    0.11
    ëĭ¤ê°Ģ
    0.10
    óg
    0.09
    ãģĨãģ¡
    0.09
     ÑĢÑıд
    0.09
    ä»ĬåĽŀ
    0.09
    ilded
    0.09
    çĪ»
    0.09
    å¾®åķĨ
    0.08
    деÑģÑıÑĤ
    0.08
    Activations Density 0.473%

    No Known Activations