© 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. 51791
    Prev
    Next
    INDEX
    Explanations

    qualified person or profession

    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
    lington
    -0.10
    oyo
    -0.10
    解æĶ¾æĢĿæĥ³
    -0.09
    åĦ¿
    -0.09
    ystate
    -0.09
    uristic
    -0.08
    uces
    -0.08
    ÙĪب
    -0.08
    æī£
    -0.08
    egg
    -0.08
    POSITIVE LOGITS
    atter
    0.10
    tte
    0.09
    .INVALID
    0.09
    _sid
    0.08
    UTURE
    0.08
    issy
    0.08
    ierung
    0.08
    itty
    0.08
    itative
    0.08
    icious
    0.08
    Activations Density 0.032%

    No Known Activations