© 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. 18790
    Prev
    Next
    INDEX
    Explanations

    helm station, helm upgrades, helminths

    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
    erate
    -0.09
    ly
    -0.09
    omorphic
    -0.09
    weet
    -0.08
    atem
    -0.08
    doch
    -0.08
    ary
    -0.08
    aled
    -0.08
    owed
    -0.08
    oice
    -0.08
    POSITIVE LOGITS
    manship
    0.13
    ä¸ĬçļĦ
    0.10
    erson
    0.10
    isphere
    0.10
    lessly
    0.10
    LESS
    0.09
    åĩĽ
    0.09
    åİļåİļçļĦ
    0.09
    íĮ©
    0.09
     ÑĥпÑĢавлениÑı
    0.09
    Activations Density 0.002%

    No Known Activations