© 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. 39501
    Prev
    Next
    INDEX
    Explanations

    accept or receive input/data

    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
    reon
    -0.09
     midway
    -0.09
    oir
    -0.08
    æĪijçľĭ
    -0.08
    享
    -0.08
    reation
    -0.08
    箩
    -0.08
    æī¯
    -0.08
    pest
    -0.08
    ried
    -0.08
    POSITIVE LOGITS
    æĿ¥èĩª
    0.12
    ä¾Ĩèĩª
    0.11
    è¾ĵåħ¥
    0.11
    æī¿åıĹ
    0.10
    åľ¨æİ¥åıĹ
    0.10
    æİ¥åıĹ
    0.10
    åĪ°æĿ¥
    0.10
    ứ
    0.10
     inputs
    0.10
    _input
    0.09
    Activations Density 0.120%

    No Known Activations