© 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. 1103
    Prev
    Next
    INDEX
    Explanations

    in order to

    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
    .Localization
    -0.09
    ç¼ij
    -0.09
    HING
    -0.09
     CIM
    -0.09
    bourne
    -0.08
    angs
    -0.08
    .ci
    -0.08
    åħ±åIJĮåıijå±ķ
    -0.08
    eneg
    -0.08
    åĺİ
    -0.08
    POSITIVE LOGITS
    itate
    0.10
    ä¸į妨
    0.09
    åĪĨåĪ«æĺ¯
    0.09
    zar
    0.09
    ä¸įè¿ľ
    0.09
    åĪĨåĪ«
    0.09
    ä¸įçĶ¨
    0.08
    é²ľèĬ±
    0.08
    è¯
    0.08
    olie
    0.08
    Activations Density 0.018%

    No Known Activations