© 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. 1571
    Prev
    Next
    INDEX
    Explanations

    obscene, vulgar, immoral, crude activities

    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
    zed
    -0.22
    ced
    -0.21
    å¾Īæ£Ĵ
    -0.21
     cozy
    -0.20
    .history
    -0.20
    rello
    -0.20
    ç²¾éĢļ
    -0.20
    asca
    -0.20
    -history
    -0.19
    history
    -0.19
    POSITIVE LOGITS
     Prosecutor
    0.23
    è¨Ģ论
    0.23
    秽
    0.23
    ulence
    0.22
    ÑĢоÑģ
    0.22
     hại
    0.21
    jas
    0.21
     prosecutor
    0.21
     posture
    0.21
    rape
    0.20
    Activations Density 0.003%

    No Known Activations