© 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. 61987
    Prev
    Next
    INDEX
    Explanations

    credit or attribution

    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
    _matching
    -0.09
    æģ¶
    -0.09
    å¡Ķ
    -0.09
    磫
    -0.09
    ãĦ´
    -0.09
    èįIJ
    -0.08
    夹
    -0.08
    çŃ¾åIJį
    -0.08
    åĩ¿
    -0.08
    æĺŁæĺŁ
    -0.08
    POSITIVE LOGITS
    [source
    0.09
    åĩºåıij
    0.09
    æºIJæ³ī
    0.09
    èIJ±
    0.09
    ajas
    0.09
    à¸į
    0.09
    å½ĵåį³
    0.08
    source
    0.08
    éĹ®æĪij
    0.08
     source
    0.08
    Activations Density 0.021%

    No Known Activations