© 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. 32274
    Prev
    Next
    INDEX
    Explanations

    much more

    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
    urations
    -0.09
    åŃĹ第
    -0.09
    çļĦå¿ĥæĥħ
    -0.09
    追究
    -0.08
    ç¥ĸ
    -0.08
    æıŃ示
    -0.08
    6
    -0.08
    ickey
    -0.08
     Fou
    -0.08
     sob
    -0.08
    POSITIVE LOGITS
    läss
    0.10
    ahan
    0.09
    ahas
    0.09
    çĬĩ
    0.08
    宣æī¬
    0.08
    éĺĩ
    0.08
    æĿ¥æºIJ
    0.08
    lamp
    0.08
    éģĹ
    0.08
    æĪij以为
    0.08
    Activations Density 0.011%

    No Known Activations