© 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. 5476
    Prev
    Next
    INDEX
    Explanations

    written permission, informed consent

    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
    èĥŀ
    -0.09
    åij¼
    -0.08
    ÑģÑĤеÑĢ
    -0.08
    punk
    -0.08
     drinks
    -0.08
    gence
    -0.08
    alm
    -0.08
    -0.08
    ordo
    -0.08
    urr
    -0.08
    POSITIVE LOGITS
    ed
    0.10
    èľĴ
    0.09
    ijn
    0.09
    éģIJ
    0.08
    -only
    0.08
    agan
    0.08
    æµ·æ¹¾
    0.08
    è¶ħ强
    0.08
    éĢĢåĽŀ
    0.08
    _sd
    0.08
    Activations Density 0.019%

    No Known Activations