© 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. 33840
    Prev
    Next
    INDEX
    Explanations

    education

    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
    åĦ¿
    -0.11
    à¹Ĩ
    -0.10
    azo
    -0.10
    ness
    -0.10
    hood
    -0.10
    ter
    -0.10
    ãģĹãĤĩãģĨ
    -0.09
    çľģæķĻèĤ²åİħ
    -0.09
    itude
    -0.09
    ä»ŀ
    -0.09
    POSITIVE LOGITS
    ally
    0.18
    ALLY
    0.13
    å·¥ä½ľèĢħ
    0.11
    agger
    0.10
    scape
    0.10
    ëŁī
    0.09
    anse
    0.09
    ç½ijå°ıç¼ĸ
    0.09
    wig
    0.09
    tas
    0.09
    Activations Density 0.034%

    No Known Activations