© 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. 39050
    Prev
    Next
    INDEX
    Explanations

    contact us so

    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
    charm
    -0.09
    æĿµ
    -0.08
    ilated
    -0.08
    åľ¨æĪij
    -0.08
    æĪĹ
    -0.08
     Crate
    -0.08
    ë±ħ
    -0.08
    oker
    -0.08
    è§Ī
    -0.08
     FRE
    -0.08
    POSITIVE LOGITS
    .opensource
    0.10
    åģļä¸ĢäºĽ
    0.10
    帮ä»ĸ
    0.10
    æĪij认为
    0.09
    ç®ĢåİĨ
    0.09
    以便
    0.09
    Alg
    0.09
    éĸ£
    0.09
    _TYP
    0.09
    alg
    0.09
    Activations Density 0.043%

    No Known Activations