© 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. 31859
    Prev
    Next
    INDEX
    Explanations

    PBS, pb, Bart, paste

    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
    ä¸Ĭå²Ĺ
    -0.12
    éĴ¤
    -0.11
    åŁİ管
    -0.10
    ature
    -0.09
    æĬ¥ç¤¾
    -0.09
    æĸĩåĮĸä¼łåªĴ
    -0.09
    á»ĵng
    -0.08
    å³Ħ
    -0.08
    pler
    -0.08
    oret
    -0.08
    POSITIVE LOGITS
    ики
    0.09
     вÑĭÑģоко
    0.09
    isu
    0.09
    emics
    0.08
    .addButton
    0.08
    æŃ£åĵģ
    0.08
    gne
    0.08
    .twimg
    0.08
    oins
    0.08
    iona
    0.08
    Activations Density 0.005%

    No Known Activations