© 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. 32317
    Prev
    Next
    INDEX
    Explanations

    much, many, amount

    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
    æĪ¡
    -0.09
    éĻĤ
    -0.09
    çīĪæĿĥ声æĺİ
    -0.09
    æIJ½
    -0.09
    âļĵ
    -0.09
    cko
    -0.09
    IVA
    -0.09
    /or
    -0.08
    onds
    -0.08
    渤
    -0.08
    POSITIVE LOGITS
    Ļ
    0.10
    å¸ĥå°Ķ
    0.09
     jose
    0.08
    åį¿
    0.08
    uv
    0.08
    åĦ¿
    0.08
    åĬłæĭ¿
    0.08
    rush
    0.08
    åģļ个
    0.07
    羣å¿ĥ
    0.07
    Activations Density 0.009%

    No Known Activations