© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 38233
    Prev
    Next
    INDEX
    Explanations

    pal / palm prefixes

    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
    ildo
    -0.10
    edList
    -0.10
    ori
    -0.10
    oses
    -0.10
    opher
    -0.09
    esti
    -0.09
    esters
    -0.09
    abouts
    -0.09
    odom
    -0.09
    áĥ§
    -0.09
    POSITIVE LOGITS
    impse
    0.13
    igned
    0.11
    indrome
    0.10
    ows
    0.09
    对ä¸įèµ·
    0.09
    Ñģад
    0.09
    acios
    0.09
    ermo
    0.09
    绾
    0.09
    éģĵçIJĨ
    0.09
    Activations Density 0.032%

    No Known Activations