© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 20038
    Prev
    Next
    INDEX
    Explanations

    sale or selling

    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
    èİ«åIJįåħ¶å¦Ļ
    -0.10
    亲åıĭ
    -0.09
    .symmetric
    -0.09
    æ¦ķ
    -0.09
    (Sender
    -0.08
    plates
    -0.08
    ofire
    -0.08
    _arrays
    -0.08
    åĨ¤
    -0.08
    æħİ
    -0.08
    POSITIVE LOGITS
    è¿Ļ件
    0.11
    åĩºåĶ®
    0.10
    лей
    0.10
    婧
    0.10
    åĶ®åįĸ
    0.10
    åįĸç»Ļ
    0.10
    ini
    0.09
    åľ¨å¸Ĥåľºä¸Ĭ
    0.09
    åĬ³åĬ¨åĬĽ
    0.09
    iba
    0.09
    Activations Density 0.053%

    No Known Activations