© 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. 8007
    Prev
    Next
    INDEX
    Explanations

    robot and robotics 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
    åĢ¬
    -0.11
    代表æĢ§
    -0.09
    bsites
    -0.09
    loe
    -0.09
    OfFile
    -0.09
     dÃłng
    -0.09
    erator
    -0.09
    grounds
    -0.09
    coc
    -0.08
    oner
    -0.08
    POSITIVE LOGITS
    ically
    0.13
    ics
    0.11
    arium
    0.11
    -readable
    0.09
    ulous
    0.09
    ype
    0.09
    ique
    0.08
    ees
    0.08
    iqu
    0.08
     Jeb
    0.08
    Activations Density 0.008%

    No Known Activations