© 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. 11509
    Prev
    Next
    INDEX
    Explanations

    automatically generated code

    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
    baum
    -0.10
    .getMap
    -0.08
    ç½ij讯
    -0.08
    ensex
    -0.08
    /method
    -0.08
    Ñħож
    -0.08
    lon
    -0.07
    ASP
    -0.07
    大æĸ¹
    -0.07
    jes
    -0.07
    POSITIVE LOGITS
    ucle
    0.10
    åĢĮ
    0.09
    çĶ¨æĪ·æıIJä¾Ľ
    0.09
    åĶĶ
    0.09
    çģ«çĪĨ
    0.09
    表çĻ½
    0.08
     ÑģÑĩиÑĤа
    0.08
    没æľīä»Ģä¹Ī
    0.08
    ç¶ļãģįãĤĴèªŃãĤĢ
    0.08
    绣çŃ¹æİ¨è¿Ľ
    0.08
    Activations Density 0.701%

    No Known Activations