© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 52683
    Prev
    Next
    INDEX
    Explanations

    back compounds

    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
    моÑĢ
    -0.10
    errer
    -0.10
     ÑĤÑĭ
    -0.10
    åĩ¤
    -0.09
    è´½
    -0.09
    ãģĦãģŁãĤī
    -0.09
    ASE
    -0.09
    ctions
    -0.09
    ãģĤãĤĬãģĮãģ¨ãģĨ
    -0.09
    çłº
    -0.09
    POSITIVE LOGITS
    =back
    0.10
    .Back
    0.09
     back
    0.09
    ronym
    0.09
    (back
    0.09
    slashes
    0.09
    slash
    0.08
     atrás
    0.08
     backs
    0.08
    tracking
    0.08
    Activations Density 0.046%

    No Known Activations