© 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. 11038
    Prev
    Next
    INDEX
    Explanations

    cocktail or cockpit

    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
    lessly
    -0.10
    æľµ
    -0.09
    wide
    -0.09
    éĻħ
    -0.09
    CAPE
    -0.08
    noch
    -0.08
    ders
    -0.08
    ovie
    -0.08
    itted
    -0.08
     afar
    -0.08
    POSITIVE LOGITS
    ï¸
    0.12
    rooms
    0.10
    é»ĺå¥ij
    0.10
    身亡
    0.10
    æĤ¨åı¯ä»¥
    0.09
    eries
    0.09
    ä»Ģä¹Īåı«
    0.09
    StatusLabel
    0.09
    æ®ĩ
    0.09
    gether
    0.09
    Activations Density 0.004%

    No Known Activations