© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 21100
    Prev
    Next
    INDEX
    Explanations

    numbers followed by units

    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
    ades
    -0.09
    FREE
    -0.08
    åįģä¸ī
    -0.08
    Reminder
    -0.07
    ÑģÑĤÑĢой
    -0.07
    æ··åĩĿ
    -0.07
    ç¼ĺ
    -0.07
    oine
    -0.07
    ä¸į解
    -0.07
    EP
    -0.07
    POSITIVE LOGITS
    äºĶçĻ¾
    0.13
    ä¸īåįĥ
    0.13
    äºĶåįĥ
    0.11
    ä¸Ģåįĥ
    0.11
    两åįĥ
    0.11
    icom
    0.10
    æī¯
    0.10
    糧
    0.09
    SED
    0.09
    isel
    0.09
    Activations Density 0.181%

    No Known Activations