© 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. 17555
    Prev
    Next
    INDEX
    Explanations

    tinting and hues

    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
    å¤§éĽ¨
    -0.10
    zyst
    -0.10
    mente
    -0.09
    ðŁı»
    -0.08
    主義
    -0.08
    бÑĭ
    -0.08
    ðŁı¼
    -0.08
    æŶ任
    -0.08
    -readable
    -0.08
    æĢ§åij½
    -0.08
    POSITIVE LOGITS
    enance
    0.10
    ê¹Ķ
    0.09
    eno
    0.09
    ening
    0.08
    obot
    0.08
    ligt
    0.08
    åĩłåĪĨ
    0.08
    pering
    0.08
     sá»Ńa
    0.08
    æł¼å°Ķ
    0.08
    Activations Density 0.006%

    No Known Activations