© 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. 23744
    Prev
    Next
    INDEX
    Explanations

    toll related phrases

    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
    ially
    -0.12
     tense
    -0.11
    ../../../
    -0.10
    hood
    -0.10
    rlen
    -0.09
    iddle
    -0.09
    ?action
    -0.09
     DUP
    -0.09
    atables
    -0.09
    çķĮçļĦ
    -0.09
    POSITIVE LOGITS
    ingly
    0.12
    led
    0.11
    ×ķת
    0.10
    ing
    0.10
    ãģ¾ãģ¾
    0.10
    ãģĹãģ¾ãģĦ
    0.10
    enance
    0.10
    ãģĹãģ¾ãģĨ
    0.10
    roads
    0.10
    sed
    0.09
    Activations Density 0.022%

    No Known Activations