© 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. 57324
    Prev
    Next
    INDEX
    Explanations

    Ashland/Ashton names and places

    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
    istar
    -0.10
    룡
    -0.10
    åī¯å±Ģéķ¿
    -0.10
    wyn
    -0.10
    xing
    -0.10
    建设çĶ¨åľ°
    -0.10
     знаÑĤÑĮ
    -0.09
    éĦ£
    -0.09
    xes
    -0.09
    erver
    -0.09
    POSITIVE LOGITS
    ../../../
    0.12
    imes
    0.10
    OrUpdate
    0.09
    opia
    0.09
    utz
    0.08
    åĪ©äºİ
    0.08
    oken
    0.08
    é¢ı
    0.08
    shire
    0.08
    èĥ½å¾ĹåĪ°
    0.08
    Activations Density 0.008%

    No Known Activations