© 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. 48055
    Prev
    Next
    INDEX
    Explanations

    dates and numbers

    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
    çĺ«
    -0.08
    gere
    -0.07
    åĿļå®ļä¸į
    -0.07
     pec
    -0.07
    -
    -0.07
    Stamp
    -0.07
    ...
    -0.07
     stamp
    -0.07
    ologically
    -0.07
     apt
    -0.07
    POSITIVE LOGITS
    astreet
    0.11
    éĶ·
    0.11
    KANJI
    0.10
    å°ıåĦ¿
    0.10
    lluminate
    0.10
    äºĶæľĪ
    0.10
    Ù¸
    0.10
    lashes
    0.10
    scriptId
    0.10
    缮çļĦæĺ¯
    0.10
    Activations Density 0.380%

    No Known Activations