© 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. 1845
    Prev
    Next
    INDEX
    Explanations

    make a saving throw

    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
     warmly
    -0.25
     Twin
    -0.24
    ortho
    -0.23
    å°ģéĹŃ
    -0.23
    ç»ĪçĶŁ
    -0.23
    å£ģ纸
    -0.23
    å¤īãģĪ
    -0.23
    åĽ½ç±į
    -0.23
    æ·±
    -0.23
    æłĸ
    -0.23
    POSITIVE LOGITS
     calculations
    0.31
    Attempt
    0.29
    æĪIJåĬŁçİĩ
    0.29
     probability
    0.28
     verbal
    0.28
     verbs
    0.27
    Failure
    0.27
     ratings
    0.27
    Outcome
    0.27
    æĥħå¢ĥ
    0.27
    Activations Density 0.045%

    No Known Activations