© 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. 30398
    Prev
    Next
    INDEX
    Explanations

    elected to represent

    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
    åħ¨åijĺ
    -0.10
    ÑĤиÑĢ
    -0.09
    _ELEMENTS
    -0.09
    çªĴæģ¯
    -0.09
    侮辱
    -0.09
     drib
    -0.09
    çĤ¹æ»´
    -0.08
    _LOGGER
    -0.08
    æ®Ħ
    -0.08
    éĻĽä¸ĭ
    -0.08
    POSITIVE LOGITS
    为æ°ij
    0.11
     serving
    0.10
    è®®åijĺ
    0.10
     serve
    0.10
     serves
    0.09
     Serve
    0.09
    æ°ij
    0.09
    éĢĢ
    0.09
     elected
    0.09
    åIJİæĿ¥
    0.08
    Activations Density 0.329%

    No Known Activations