© 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. 57937
    Prev
    Next
    INDEX
    Explanations

    show support

    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
     VOID
    -0.09
    æ¯ıä¸Ģ
    -0.08
    åħī线
    -0.08
    lad
    -0.08
    纵横
    -0.08
    ળ
    -0.08
    éĶ»
    -0.08
    Void
    -0.08
    gratis
    -0.08
     dashes
    -0.08
    POSITIVE LOGITS
    åħ³æĢĢ
    0.12
    sted
    0.10
    çĥŃæĥħ
    0.10
    çIJĨ解åĴĮ
    0.09
    æİĴæĸ¥
    0.09
     support
    0.09
    _SUPPORT
    0.09
    åħ³åĪĩ
    0.09
    稳妥
    0.09
    DataManager
    0.09
    Activations Density 0.023%

    No Known Activations