© 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. 7399
    Prev
    Next
    INDEX
    Explanations

    cluster headaches, GitLab, or factory

    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
    sworth
    -0.10
    isto
    -0.09
    å£ķ
    -0.09
    ила
    -0.09
    ж
    -0.09
    éĥ¨
    -0.09
    licity
    -0.08
    ardo
    -0.08
    acious
    -0.08
    zzle
    -0.08
    POSITIVE LOGITS
    ingly
    0.12
    buster
    0.12
    åĨħçļĦ
    0.11
    å·į
    0.10
    виÑĤ
    0.10
    wide
    0.10
    ions
    0.10
    ł
    0.09
    rok
    0.09
    hips
    0.09
    Activations Density 0.028%

    No Known Activations