© 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. 22764
    Prev
    Next
    INDEX
    Explanations

    adding, adds, make

    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
    <Scalar
    -0.09
    æĶĺ
    -0.09
    ALLE
    -0.09
    ault
    -0.09
    _AUX
    -0.09
    _VENDOR
    -0.09
    è´§æºIJ
    -0.09
    PRINTF
    -0.09
    头æĿ¡
    -0.09
    Commerce
    -0.09
    POSITIVE LOGITS
    夺
    0.08
    8
    0.08
     tail
    0.08
    æĤłä¹ħ
    0.08
    4
    0.08
    3
    0.08
    icted
    0.08
    0
    0.08
    2
    0.08
    5
    0.08
    Activations Density 0.045%

    No Known Activations