© 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. 51279
    Prev
    Next
    INDEX
    Explanations

    Core extensions

    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
    cock
    -0.10
    åĪĿæģĭ
    -0.09
    ersive
    -0.09
    raphic
    -0.08
    èĢĥæł¸
    -0.08
    ackson
    -0.08
    äºĨä¸Ģåı¥
    -0.08
    _datasets
    -0.08
     visa
    -0.08
    adar
    -0.08
    POSITIVE LOGITS
    /Core
    0.12
    (Core
    0.12
    æł¸å¿ĥ
    0.12
     core
    0.12
    CORE
    0.11
    /core
    0.11
    ndon
    0.11
    (core
    0.11
     Core
    0.11
    -core
    0.10
    Activations Density 0.072%

    No Known Activations