© 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. 1461
    Prev
    Next
    INDEX
    Explanations

    better/worse comparisons

    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
    æŁIJç§į
    -0.24
    partial
    -0.24
    sut
    -0.23
     partial
    -0.23
    ail
    -0.23
    -authored
    -0.22
    Bro
    -0.22
    rail
    -0.22
    aily
    -0.21
    -prop
    -0.21
    POSITIVE LOGITS
    åĴĮå®ĮåĸĦ
    0.30
    åĴĮåıijå±ķ
    0.28
    /change
    0.25
    è¶ĬæĿ¥è¶Ĭ好
    0.23
    åĴĮæĶ¯æĮģ
    0.21
    ä¸İåıijå±ķ
    0.21
    å°±è¶Ĭ
    0.20
     leaps
    0.20
    endors
    0.20
    æ°´åŁŁ
    0.20
    Activations Density 0.018%

    No Known Activations