© 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. 2981
    Prev
    Next
    INDEX
    Explanations

    physical arrangement and construction

    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
    æ±ł
    -0.24
    oad
    -0.24
    幡
    -0.22
    icates
    -0.21
     pilot
    -0.21
    NC
    -0.21
    ä¸įåĪ°
    -0.21
    è¯ķ
    -0.21
    æīĺ
    -0.21
     tangible
    -0.21
    POSITIVE LOGITS
    çµIJæ§ĭ
    0.36
    /design
    0.35
    -wise
    0.35
    /format
    0.35
     structure
    0.35
    /function
    0.33
    ç»ĵæŀĦ
    0.33
    çī¹çĤ¹
    0.32
    åĴĮæĬĢæľ¯
    0.31
    _structure
    0.31
    Activations Density 0.293%

    No Known Activations