© 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. 30667
    Prev
    Next
    INDEX
    Explanations

    life spans

    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
    ness
    -0.12
    棣
    -0.12
    ment
    -0.11
    lah
    -0.11
    illions
    -0.10
    ãģĦãĤĭ
    -0.10
    çĶŁåij½åĬĽ
    -0.10
    aurus
    -0.10
    æĸ¯åĿ¦
    -0.10
    åĮ¹
    -0.10
    POSITIVE LOGITS
    boat
    0.17
    -threatening
    0.13
    boats
    0.12
    fully
    0.12
     expectancy
    0.12
    -même
    0.11
    fty
    0.11
    blood
    0.11
    0.11
    lessness
    0.11
    Activations Density 0.060%

    No Known Activations