© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 53048
    Prev
    Next
    INDEX
    Explanations

    Ella and Louis

    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
    åįĴ
    -0.09
    located
    -0.09
    éĤij
    -0.08
    rust
    -0.08
    abouts
    -0.08
     bust
    -0.08
    åŁ½
    -0.08
    éĻ¢æł¡
    -0.07
    niÄĻ
    -0.07
     Webb
    -0.07
    POSITIVE LOGITS
     dÃłng
    0.10
    æķ£åıij
    0.10
    inha
    0.09
    ulle
    0.09
    ivant
    0.09
    æĴ¸
    0.09
    åĻ«
    0.09
    æĹĭ
    0.09
    å¾Ĵ
    0.09
     игÑĢов
    0.09
    Activations Density 0.004%

    No Known Activations