© 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. 1885
    Prev
    Next
    INDEX
    Explanations

    high school career/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
    æĭĸ
    -0.27
    以åIJİ
    -0.23
     Independ
    -0.23
    ç»Ŀ
    -0.22
    åIJĪä½ľ
    -0.22
    çĭŃ
    -0.22
     leading
    -0.22
    寸
    -0.22
    Phys
    -0.22
     dick
    -0.21
    POSITIVE LOGITS
    _pcm
    0.25
    æĸ°ä¸ī
    0.24
    rts
    0.22
    æľįåĭĻæĪĸ
    0.22
     TSR
    0.21
     motives
    0.21
    =__
    0.21
    æĥ³å¿µ
    0.21
     chewing
    0.21
    swick
    0.21
    Activations Density 0.001%

    No Known Activations