© 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. 58669
    Prev
    Next
    INDEX
    Explanations

    names followed by initials or last names

    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
    éħĭ
    -0.10
    ual
    -0.09
    keit
    -0.09
    ä¸ĭæĿ¥çļĦ
    -0.09
    ITE
    -0.08
    ASTE
    -0.08
    ivity
    -0.08
    ting
    -0.08
    indexed
    -0.08
    uffs
    -0.08
    POSITIVE LOGITS
    iling
    0.10
    apter
    0.10
    ered
    0.09
    liness
    0.09
    itzer
    0.09
    tape
    0.09
    eron
    0.09
    er
    0.09
    cial
    0.08
    acho
    0.08
    Activations Density 0.012%

    No Known Activations