© 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. 1502
    Prev
    Next
    INDEX
    Explanations

    set to followed by a verb

    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
    å¸ĮæľĽèĥ½
    -0.10
    /to
    -0.09
    oen
    -0.08
    able
    -0.08
    avid
    -0.08
    ä¸įçĶ¨
    -0.08
    spy
    -0.08
    athy
    -0.08
    åİŁåĪĻä¸Ĭ
    -0.08
    anke
    -0.08
    POSITIVE LOGITS
    æĪĸå¤ļ
    0.10
    åľ¨æ¸¸æĪıä¸Ń
    0.09
    åĮ»ç§ij大åѦ
    0.09
     forth
    0.09
    人çĶŁ
    0.09
    è¿Ļä¹Īåģļ
    0.08
    nd
    0.08
    CADE
    0.08
    ature
    0.08
    æĹº
    0.08
    Activations Density 0.010%

    No Known Activations