© 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. 7078
    Prev
    Next
    INDEX
    Explanations

    morale, confidence, sentiment, spirit

    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
    finger
    -0.09
    noch
    -0.09
    oni
    -0.08
    uh
    -0.08
    ings
    -0.08
    IME
    -0.08
    erek
    -0.08
    ected
    -0.08
    ÑĮ
    -0.08
    ING
    -0.08
    POSITIVE LOGITS
    åĭĥåĭĥ
    0.11
    åįģ足
    0.10
    åħħæ²Ľ
    0.10
    ìħĭ
    0.10
    æĮĪ
    0.10
    建设åĴĮ
    0.10
    满满
    0.10
    apolis
    0.09
    补水
    0.09
    OTES
    0.09
    Activations Density 0.003%

    No Known Activations