© 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. 18268
    Prev
    Next
    INDEX
    Explanations

    problem -solving

    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
    ubi
    -0.10
    yard
    -0.10
    robe
    -0.10
    atures
    -0.09
    åĬŁå¤«
    -0.09
    elines
    -0.09
    urance
    -0.09
    æĥ³æī¾
    -0.09
    eday
    -0.09
    ature
    -0.09
    POSITIVE LOGITS
    atic
    0.11
    -solving
    0.09
    niejs
    0.09
    æ¹ĥ
    0.09
     latter
    0.09
    ราว
    0.09
    atics
    0.09
    stellung
    0.09
    ¥
    0.08
    /question
    0.08
    Activations Density 0.056%

    No Known Activations