© 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. 8245
    Prev
    Next
    INDEX
    Explanations

    access or accessing something

    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
    est
    -0.09
    佬
    -0.09
    æ¦Ķ
    -0.09
    quee
    -0.09
    amespace
    -0.09
    town
    -0.09
    ×ķת
    -0.09
    aily
    -0.09
    ather
    -0.09
    anny
    -0.09
    POSITIVE LOGITS
    OrCreate
    0.15
    ible
    0.12
    ioned
    0.12
    ibly
    0.11
    amp
    0.11
    ivity
    0.10
     Oval
    0.10
    ories
    0.10
    IBLE
    0.10
    sing
    0.10
    Activations Density 0.054%

    No Known Activations