© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 50710
    Prev
    Next
    INDEX
    Explanations

    eccentric person or thing

    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
    rock
    -0.09
    .syntax
    -0.08
    Senior
    -0.08
    _INTR
    -0.08
    çģ°èī²
    -0.08
    ÑĩÑĮ
    -0.08
    èºį
    -0.08
    ponce
    -0.08
    çon
    -0.08
     Symphony
    -0.07
    POSITIVE LOGITS
    ities
    0.16
    ally
    0.13
    ity
    0.13
    ALLY
    0.11
    lah
    0.11
    loff
    0.10
    es
    0.10
    LOUR
    0.10
    losure
    0.09
    lical
    0.09
    Activations Density 0.010%

    No Known Activations