© 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. 2306
    Prev
    Next
    INDEX
    Explanations

    names and titles ending words

    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
     booths
    -0.26
     married
    -0.23
    ITHER
    -0.23
    å¾ĹçĽĬ
    -0.22
    ordinate
    -0.21
    åĴĮå®ĮåĸĦ
    -0.21
     upright
    -0.20
    nets
    -0.20
    裹
    -0.20
     tickets
    -0.20
    POSITIVE LOGITS
    ä¸įç»ı
    0.26
    (async
    0.23
    ensed
    0.22
    æľªç»ı
    0.22
    suite
    0.22
    ian
    0.22
    æĬ¤èº«ç¬¦
    0.21
    osite
    0.21
    罪
    0.21
    iest
    0.21
    Activations Density 0.002%

    No Known Activations