© 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. 30022
    Prev
    Next
    INDEX
    Explanations

    fear or fearing followed by that

    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
    çħ
    -0.10
    -Sah
    -0.09
    говоÑĢ
    -0.09
    ãģĹãģ¾ãģĦ
    -0.08
    ãģĹãģ¾ãģĨ
    -0.08
    ersen
    -0.08
    åĤ»
    -0.08
     Oven
    -0.08
    evity
    -0.08
    æĿŁ
    -0.08
    POSITIVE LOGITS
    lessly
    0.17
    fully
    0.13
    ingly
    0.12
    less
    0.10
    iest
    0.10
    ably
    0.09
    лав
    0.09
    ful
    0.09
    à¸ĩาà¸Ļ
    0.08
    :Number
    0.08
    Activations Density 0.011%

    No Known Activations