© 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. 1971
    Prev
    Next
    INDEX
    Explanations

    Eminem, Hood, Al, Man

    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
    åĵģåij³
    -0.25
     equipments
    -0.23
    Tau
    -0.22
    èī²è°ĥ
    -0.22
     seaw
    -0.22
    èľĤèľľ
    -0.22
    sects
    -0.21
    éĥ¨ä»½
    -0.21
    adir
    -0.21
     however
    -0.21
    POSITIVE LOGITS
     pop
    0.22
    atorio
    0.22
    antal
    0.22
    AMES
    0.21
    né
    0.21
    oz
    0.21
    åĨĴ
    0.21
    ivi
    0.21
    lich
    0.21
     Unicode
    0.21
    Activations Density 0.002%

    No Known Activations