© 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. 11176
    Prev
    Next
    INDEX
    Explanations

    names and specific entities

    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
    æľµ
    -0.10
    WebRequest
    -0.09
    isans
    -0.09
    åīģ
    -0.09
    swick
    -0.08
    aha
    -0.08
    angen
    -0.08
    æīįåıijçİ°
    -0.08
     Claud
    -0.08
    èĥĮä¸Ĭ
    -0.08
    POSITIVE LOGITS
    èĢģ人
    0.09
     Jinping
    0.09
    æĭ´
    0.09
    raw
    0.08
    夫å¦ĩ
    0.08
    رÙĪس
    0.08
    å®ľ
    0.08
    Ton
    0.08
    underscore
    0.08
     Rolls
    0.08
    Activations Density 0.003%

    No Known Activations