© 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. 49491
    Prev
    Next
    INDEX
    Explanations

    words starting with "per"

    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
    æĥĬ
    -0.11
    ãģĴ
    -0.10
    etten
    -0.10
    dek
    -0.09
    бÑĢи
    -0.08
     Jame
    -0.08
    abee
    -0.08
    ÑĤики
    -0.08
    боÑĤ
    -0.08
    è¡Ķ
    -0.08
    POSITIVE LOGITS
    éĥ½è§īå¾Ĺ
    0.09
     per
    0.09
     заÑĢ
    0.09
    st
    0.09
    fi
    0.08
    -
    0.08
    /per
    0.08
    èĭ«
    0.08
    inent
    0.08
    ipher
    0.08
    Activations Density 0.030%

    No Known Activations