© 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. 19217
    Prev
    Next
    INDEX
    Explanations

    wide range or variety

    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
    umps
    -0.10
    swer
    -0.10
     здоÑĢовÑĮÑı
    -0.09
    spiel
    -0.09
    èķĬ
    -0.09
    æĹ¥çĽĬ
    -0.09
    antine
    -0.08
    èĩªåįij
    -0.08
    顶å±Ĥ
    -0.08
    ors
    -0.08
    POSITIVE LOGITS
    -ranging
    0.15
    pread
    0.14
     rãi
    0.13
    -angle
    0.11
    -eyed
    0.11
    -mouth
    0.11
    广
    0.10
    anging
    0.10
    éĻĮ
    0.10
    ÑģÑĮ
    0.10
    Activations Density 0.038%

    No Known Activations