© 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
    2. Qwen3-32B
    3. 32-RESID-BATCHTOPK-65K
    4. 20695
    Prev
    Next
    INDEX
    Explanations

    space availability

    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
    å¤ĸè§Ĥ
    -0.11
    shan
    -0.10
    涯
    -0.10
    tes
    -0.09
    èĬ
    -0.09
    atham
    -0.09
    å®¶åĬ¡
    -0.09
    æĿĮ
    -0.09
    laps
    -0.09
    ä¿Ĺ
    -0.09
    POSITIVE LOGITS
    hips
    0.10
    -temp
    0.09
    flight
    0.09
    SpaceItem
    0.09
    (space
    0.09
     Ñģобой
    0.09
     зло
    0.09
    walker
    0.09
     space
    0.09
    ipo
    0.08
    Activations Density 0.090%

    No Known Activations