© 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. 31853
    Prev
    Next
    INDEX
    Explanations

    foreclosure or foreground

    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
    ãģĬ
    -0.11
    ãģĤãģ£ãģŁ
    -0.10
    ëģĶ
    -0.10
    ¶
    -0.10
    侯
    -0.10
    ãģĬ話
    -0.09
    们çļĦ
    -0.09
    procs
    -0.09
    oto
    -0.09
    ãģĻãģ§ãģ«
    -0.09
    POSITIVE LOGITS
    bidden
    0.12
    ythe
    0.12
    ering
    0.10
    lund
    0.10
    imb
    0.10
    WARD
    0.09
    è¿Ļç§įæĥħåĨµ
    0.09
    emente
    0.09
    _each
    0.09
    ship
    0.09
    Activations Density 0.071%

    No Known Activations