© 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. Qwen3-8B
    5. 18-RESID-BATCHTOPK-65K__L0-80
    7. 2903
    Prev
    Next
    INDEX
    Explanations

    anger and anger management

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-8b-saes/saes_Qwen_Qwen3-8B_batch_top_k/resid_post_layer_18
    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
    rab
    -0.22
    sWith
    -0.22
    soever
    -0.21
    urations
    -0.20
    gli
    -0.20
    ä¸Ģ个好çļĦ
    -0.20
    Printing
    -0.20
    人åĵ¡
    -0.20
    åīįæīĢ
    -0.19
    riz
    -0.18
    POSITIVE LOGITS
    /fr
    0.27
    ystone
    0.26
    ful
    0.22
    ment
    0.22
    uele
    0.21
    -filled
    0.21
    old
    0.21
    asted
    0.20
    /xhtml
    0.20
    /dist
    0.19
    Activations Density 0.004%

    No Known Activations