© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 8846
    Prev
    Next
    INDEX
    Explanations

    call for or call to

    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
    éºĵ
    -0.09
    ening
    -0.09
    emails
    -0.09
    æīĵæĸŃ
    -0.08
    ord
    -0.08
    ially
    -0.08
    ental
    -0.08
    umbing
    -0.08
    evice
    -0.08
    å¸Į
    -0.08
    POSITIVE LOGITS
    oused
    0.14
    igraphy
    0.14
    culate
    0.14
    ibration
    0.11
    ifornia
    0.11
    ibrate
    0.11
    igraph
    0.10
    culated
    0.10
    ign
    0.10
    ender
    0.10
    Activations Density 0.050%

    No Known Activations