© 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. 22503
    Prev
    Next
    INDEX
    Explanations

    comp followed by word endings

    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
    -0.13
    /or
    -0.10
    æĺ¶
    -0.10
    ackson
    -0.10
    erk
    -0.10
    ably
    -0.10
    GINE
    -0.09
    instein
    -0.09
    å®Į
    -0.09
    ç½Ħ
    -0.09
    POSITIVE LOGITS
    ensation
    0.12
    licated
    0.12
    ounding
    0.11
    artment
    0.10
    озд
    0.10
    ooter
    0.09
    InChildren
    0.09
    ensively
    0.09
    cy
    0.09
     comp
    0.09
    Activations Density 0.070%

    No Known Activations