© 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. 30791
    Prev
    Next
    INDEX
    Explanations

    Translation of

    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
    est
    -0.11
    lessly
    -0.10
    ness
    -0.10
    trail
    -0.10
    å¾Ĺä½ı
    -0.09
    emente
    -0.09
    ders
    -0.09
    ler
    -0.09
    ement
    -0.08
    trak
    -0.08
    POSITIVE LOGITS
    AutoresizingMaskIntoConstraints
    0.13
     дÑĥÑħ
    0.11
    -speaking
    0.11
    LETE
    0.10
    .translate
    0.10
    è¿ĩæĿ¥
    0.10
    ä¹Łå°±æĺ¯è¯´
    0.09
    .Translate
    0.09
    èĴŁ
    0.09
    åł°
    0.09
    Activations Density 0.045%

    No Known Activations