© 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. 34183
    Prev
    Next
    INDEX
    Explanations

    quantities with halves

    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
    ró
    -0.10
    ursed
    -0.10
    éģ£
    -0.09
    úmeros
    -0.09
    çĬĢ
    -0.09
    ibri
    -0.08
    EDIA
    -0.08
    oola
    -0.08
    esis
    -0.08
    seys
    -0.08
    POSITIVE LOGITS
    ä¸ĭè¾¾
    0.09
    å³Ń
    0.08
    aurant
    0.08
    å±¹
    0.08
    大éħĴåºĹ
    0.08
    åĽ«
    0.08
    ancy
    0.08
    被èªī
    0.08
    绣çŃ¹æİ¨è¿Ľ
    0.08
    éĻ¡
    0.08
    Activations Density 0.006%

    No Known Activations