© 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. 5930
    Prev
    Next
    INDEX
    Explanations

    degrees and angles

    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
    otto
    -0.10
    _UNICODE
    -0.09
    _spacing
    -0.09
     Ä°ki
    -0.09
    antu
    -0.09
    çģ¯
    -0.09
    太éĺ³èĥ½
    -0.08
    å¼ķ导
    -0.08
    วย
    -0.08
    讲
    -0.08
    POSITIVE LOGITS
    è§Ĵ度
    0.13
     angles
    0.12
     angle
    0.11
    殿
    0.10
    ANGLE
    0.10
    els
    0.09
    ä¸īçĻ¾
    0.09
    äºĮçĻ¾
    0.09
    -angle
    0.09
    Angle
    0.09
    Activations Density 0.051%

    No Known Activations