© 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. 39266
    Prev
    Next
    INDEX
    Explanations

    essential elements

    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
    éĿ©
    -0.10
    èIJĭ
    -0.09
    mate
    -0.09
    åĺ§
    -0.08
    èĦĤ
    -0.08
    èĭ¯
    -0.08
    éħ¯
    -0.08
    壬
    -0.08
    -cover
    -0.08
    Sugar
    -0.08
    POSITIVE LOGITS
    å¾®éĩıåħĥç´ł
    0.13
    åħĥç´ł
    0.11
    éĩijå±ŀ
    0.11
    çŁ¿çī©è´¨
    0.11
    éķģ
    0.10
    _ste
    0.10
     elemental
    0.10
    à¸ĺา
    0.10
    éĴ
    0.10
    貧
    0.10
    Activations Density 0.359%

    No Known Activations