© 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. 18007
    Prev
    Next
    INDEX
    Explanations

    exact same

    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
    ä¸ĢåĪĩ
    -0.10
    á»ĩ
    -0.10
    æĺ
    -0.09
    æ®Ĩ
    -0.09
    èĢħçļĦ
    -0.09
    CreateInfo
    -0.09
    oux
    -0.09
    ohl
    -0.09
    MUX
    -0.08
    尤为
    -0.08
    POSITIVE LOGITS
    itude
    0.17
    itud
    0.14
    itudes
    0.13
    ting
    0.12
    aneous
    0.12
    ities
    0.11
    ness
    0.11
    imate
    0.10
    ingly
    0.10
    æĦıä¹īä¸ĬçļĦ
    0.10
    Activations Density 0.022%

    No Known Activations