© 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. 5797
    Prev
    Next
    INDEX
    Explanations

    outfit

    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
    ine
    -0.11
     воÑĤ
    -0.10
    ance
    -0.09
    -eyed
    -0.09
    xon
    -0.09
     Lump
    -0.09
    /cs
    -0.09
    -0.09
    few
    -0.09
    踪
    -0.08
    POSITIVE LOGITS
    ting
    0.13
    amiento
    0.10
    teen
    0.10
    Ñĩин
    0.09
    ï¸
    0.09
    te
    0.09
    assin
    0.09
    ulario
    0.08
    缴è¾ĸå¸Ĥ
    0.08
    ARCH
    0.08
    Activations Density 0.007%

    No Known Activations