© 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. 7620
    Prev
    Next
    INDEX
    Explanations

    potential for and to

    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
    elsen
    -0.11
    æķij人
    -0.10
    æѧ
    -0.10
    engo
    -0.10
    ç»ıéªĮåĢ¼
    -0.10
    å®īåħ¨éļIJæĤ£
    -0.09
    perPage
    -0.09
     infer
    -0.09
    åIJij举
    -0.09
    amba
    -0.08
    POSITIVE LOGITS
    ity
    0.11
    ities
    0.09
    ä»»ä½ķæŶåĢĻ
    0.09
    æľĢ大åĮĸ
    0.08
    asctime
    0.08
    team
    0.08
    å¼¥
    0.08
    ноÑģÑĤей
    0.08
    ty
    0.08
    arily
    0.08
    Activations Density 0.015%

    No Known Activations