© 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. 34117
    Prev
    Next
    INDEX
    Explanations

    vary depending on

    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
    æĿ¾
    -0.09
    çİĩåħĪ
    -0.08
    sters
    -0.08
    &nbsp
    -0.08
    èĺ¸
    -0.08
    ernity
    -0.08
    bury
    -0.07
    溱
    -0.07
    带头人
    -0.07
    ย
    -0.07
    POSITIVE LOGITS
    ELLOW
    0.10
    åħ¨æĹ¥åĪ¶
    0.09
    lık
    0.09
    åľºæīĢ
    0.09
    Ñģен
    0.09
    ied
    0.09
    ê·¹
    0.09
    åIJģ
    0.09
    <ll
    0.09
    iants
    0.09
    Activations Density 0.016%

    No Known Activations