© 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. 8377
    Prev
    Next
    INDEX
    Explanations

    events involving parades, marches, walks, rides, or trails

    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
     изд
    -0.09
    ãĦ
    -0.09
    ISR
    -0.08
    è¿Ļå¥Ĺ
    -0.08
    PF
    -0.08
    iry
    -0.08
    iron
    -0.08
    ragon
    -0.08
    halb
    -0.08
     budget
    -0.08
    POSITIVE LOGITS
    åĴĮå®ĮåĸĦ
    0.10
    _utc
    0.09
    ç»ĵæĿŁåIJİ
    0.09
    å®Įæ¯ķ
    0.09
    _apps
    0.09
    ers
    0.09
    åīįåĪĹ
    0.09
    åı¸é©¬
    0.09
    ière
    0.08
    æıĨ
    0.08
    Activations Density 0.012%

    No Known Activations