© 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. 54527
    Prev
    Next
    INDEX
    Explanations

    friendly

    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
    issippi
    -0.09
    ç¥ĵ
    -0.09
    mium
    -0.09
    anja
    -0.09
    ол
    -0.09
    idian
    -0.09
    oretical
    -0.09
    æŃ£åĢ¼
    -0.08
    主è¦ģåĨħ容
    -0.08
    æŁ½
    -0.08
    POSITIVE LOGITS
    Enough
    0.12
     enough
    0.12
     ÙĦÙĦغاÙĬØ©
    0.11
    town
    0.11
    amen
    0.10
    keit
    0.10
    -looking
    0.10
     Enough
    0.10
    NESS
    0.10
    liness
    0.09
    Activations Density 0.037%

    No Known Activations