© 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. 26961
    Prev
    Next
    INDEX
    Explanations

    whilst introducing contrasting ideas or activities

    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
    then
    -0.10
    -être
    -0.09
     лиÑĪÑĮ
    -0.09
    stead
    -0.09
    ducted
    -0.09
    ustria
    -0.08
    иÑģÑĤ
    -0.08
    æĹ¶ç©º
    -0.08
    upo
    -0.08
    athers
    -0.08
    POSITIVE LOGITS
    ype
    0.11
    ãģŁãĤģãģ«
    0.10
    çĦ¶æĺ¯
    0.10
    idal
    0.10
    è¿ĺå¾Ĺ
    0.09
    åĽŀäºĭ
    0.09
    entimes
    0.09
    tle
    0.09
    _WP
    0.09
    æĺ¯æĪijçļĦ
    0.09
    Activations Density 0.010%

    No Known Activations