© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 7190
    Prev
    Next
    INDEX
    Explanations

    come/bring followed by a preposition

    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
    åİĨåı²æĢ§
    -0.09
    tro
    -0.09
    ç©¿è¿ĩ
    -0.09
    åħ¬é¡·
    -0.08
    atisch
    -0.08
    强硬
    -0.08
    .rl
    -0.08
    pard
    -0.08
    ç©¿è¶Ĭ
    -0.08
    è¿Īè¿Ľ
    -0.08
    POSITIVE LOGITS
    è¯ķè¡Į
    0.10
    åįĸåľº
    0.09
    åĵŁ
    0.09
    ovo
    0.08
    åı¯èĥ½åıijçĶŁ
    0.08
    ç»ıæŁ¥
    0.08
    çłĶ究éĻ¢
    0.08
    åłĻ
    0.08
    ERIC
    0.08
    ãģªãĤĭ
    0.08
    Activations Density 0.033%

    No Known Activations