© 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. 27728
    Prev
    Next
    INDEX
    Explanations

    cancel actions

    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
    entr
    -0.10
    onom
    -0.10
    è¿ĩåħ³
    -0.10
    ument
    -0.09
    让æĤ¨
    -0.09
    å®īçĦ¶
    -0.09
    æĪIJå°±æĦŁ
    -0.09
    å§Ķå±Ī
    -0.09
    ÑĮÑĤе
    -0.09
    æī¹æ¬¡
    -0.09
    POSITIVE LOGITS
    IMAL
    0.09
    ä¸įäºĨ
    0.09
     unused
    0.09
     Unused
    0.09
    UFF
    0.09
     mor
    0.09
    -placement
    0.08
    ÑģÑħ
    0.08
    IVA
    0.08
    airo
    0.08
    Activations Density 0.007%

    No Known Activations