© 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. 5923
    Prev
    Next
    INDEX
    Explanations

    fab followed by name-like suffixes

    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
    вали
    -0.10
    zzo
    -0.09
    acey
    -0.09
     Sinai
    -0.09
     Marg
    -0.09
    еÑĩен
    -0.08
    /MIT
    -0.08
    baugh
    -0.08
    _elt
    -0.08
    Ñģлед
    -0.08
    POSITIVE LOGITS
    ../../../
    0.16
    ulously
    0.14
    ulous
    0.12
    onacci
    0.11
    rique
    0.11
    rics
    0.09
    tron
    0.09
    å°Ķ
    0.09
    ture
    0.09
    idity
    0.09
    Activations Density 0.017%

    No Known Activations