© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 20178
    Prev
    Next
    INDEX
    Explanations

    sorption 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
    èĩ¾
    -0.13
    ÙĦ
    -0.09
    plate
    -0.09
    à¹Ģห
    -0.09
    гÑĢ
    -0.09
    imir
    -0.08
    apter
    -0.08
    ties
    -0.08
    erre
    -0.08
    ãĤĤãģĨ
    -0.08
    POSITIVE LOGITS
    ening
    0.13
    ãģĴ
    0.10
    ´
    0.10
    urbed
    0.10
    inos
    0.09
    ç¥ľ
    0.09
    emes
    0.09
    á»Ńa
    0.09
    ©
    0.09
    ILON
    0.09
    Activations Density 0.361%

    No Known Activations