© 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
    2. Qwen3-32B
    3. 32-RESID-BATCHTOPK-65K
    4. 3511
    Prev
    Next
    INDEX
    Explanations

    Heath and suffixes

    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
    ../../../
    -0.12
    ç½ķ
    -0.09
    æ¹ĥ
    -0.09
    ond
    -0.09
    çīĿ
    -0.09
    mage
    -0.09
    çĦī
    -0.09
    å¯IJ
    -0.09
    teenth
    -0.08
    è¾Ī
    -0.08
    POSITIVE LOGITS
    fully
    0.13
    enticate
    0.10
    ening
    0.10
    fulness
    0.09
    ful
    0.09
    髦
    0.09
    RAL
    0.09
    lify
    0.09
    flix
    0.09
    OwnProperty
    0.09
    Activations Density 0.010%

    No Known Activations