© 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. 61051
    Prev
    Next
    INDEX
    Explanations

    Ford, Lanza, Kavanaugh

    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
    plx
    -0.10
    _pri
    -0.09
    ä¸įéĹ´æĸŃ
    -0.09
    serter
    -0.08
    äºĨåIJ§
    -0.08
    ÙĤسÙħ
    -0.08
     Examiner
    -0.08
    _STA
    -0.08
    纵横
    -0.08
     yazılı
    -0.08
    POSITIVE LOGITS
    oup
    0.09
    ä½ij
    0.08
    åIJİæĤĶ
    0.08
    è°¶
    0.08
    agna
    0.08
    SF
    0.08
    罪
    0.08
    UF
    0.08
    rarian
    0.08
    orary
    0.08
    Activations Density 0.008%

    No Known Activations