© 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. 27493
    Prev
    Next
    INDEX
    Explanations

    of the

    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
     пÑĢава
    -0.09
    obl
    -0.08
    uge
    -0.08
    alez
    -0.08
    rame
    -0.08
    .Matchers
    -0.08
    åĬ«
    -0.08
    æľŁåĨħ
    -0.08
    æĤłæĤł
    -0.08
    infinity
    -0.08
    POSITIVE LOGITS
    ets
    0.10
    urator
    0.10
    ETS
    0.09
    åįĩèµ·
    0.09
    çĶ¨åľ°
    0.09
    稳å®ļçļĦ
    0.09
    inders
    0.08
    ities
    0.08
    人æ°ijç½ij
    0.08
    车ç«Ļ
    0.08
    Activations Density 0.075%

    No Known Activations