© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 4785
    Prev
    Next
    INDEX
    Explanations

    Newport, Monterey, iTunes

    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
    onaut
    -0.09
    _SUPPORTED
    -0.09
    æī°
    -0.09
    LOT
    -0.09
    ç½ijç»ľä¼łæĴŃ
    -0.09
    íį¼
    -0.09
    èĶ¼
    -0.08
    åħ¶æīĢ
    -0.08
    jack
    -0.08
    FLAG
    -0.08
    POSITIVE LOGITS
    åĬ¨éĿĻ
    0.09
    æľīåĩłä¸ª
    0.09
    à¸Ľà¸£à¸°
    0.09
    ä»»ä½ķæŶåĢĻ
    0.08
    acic
    0.08
    isse
    0.08
    /th
    0.08
    bern
    0.08
    sv
    0.08
    侦
    0.08
    Activations Density 0.003%

    No Known Activations