© 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. 62958
    Prev
    Next
    INDEX
    Explanations

    classic followed by noun

    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
    atto
    -0.10
    edImage
    -0.09
    åŁ
    -0.09
    æĽĻåħī
    -0.09
    ered
    -0.09
    å·§
    -0.08
    åıĭ
    -0.08
    ä½°
    -0.08
    å¾Ĺèµ·
    -0.08
    ables
    -0.08
    POSITIVE LOGITS
    -minded
    0.12
    çĦľ
    0.09
    renc
    0.09
    elli
    0.09
    izing
    0.09
     оÑĦоÑĢм
    0.09
    æĭ¿æĿ¥
    0.09
     ÑĦин
    0.09
    ä¸įèĥ½åĨį
    0.09
    æĺĨ
    0.09
    Activations Density 0.009%

    No Known Activations