© 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. 2229
    Prev
    Next
    INDEX
    Explanations

    a few / a quick

    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
    èĩ³å°ij
    -0.25
     definitely
    -0.25
    IER
    -0.23
     already
    -0.23
     entire
    -0.23
     everything
    -0.22
    åĪ°åºķ
    -0.22
    .createObject
    -0.22
     deserved
    -0.22
     EVERY
    -0.21
    POSITIVE LOGITS
    åĩłæŃ¥
    0.30
    åĩłåĪĨéĴŁ
    0.27
    ä¸Ģçŀ¬éĹ´
    0.26
    åĩłå¤©
    0.25
    çīĩåĪ»
    0.25
    çŁŃçŁŃ
    0.24
    äºĽ
    0.23
    è·¬
    0.23
    们çļĦ
    0.23
    Bay
    0.23
    Activations Density 0.019%

    No Known Activations