© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-8B
    5. 18-RESID-BATCHTOPK-65K__L0-80
    7. 85
    Prev
    Next
    INDEX
    Explanations

    picking up, ask about, do it, plan the, enjoy playing, try again, make a, heading toward, get out

    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
    ç»ıéªĮåĴĮ
    -0.40
    çIJĨ解åĴĮ
    -0.38
    管çIJĨåĴĮ
    -0.30
    èĥ½åĬĽåĴĮ
    -0.28
    çĶŁäº§åĴĮ
    -0.26
    æĬĢæľ¯åĴĮ
    -0.26
    æŶéĹ´åĴĮ
    -0.26
    è´¨éĩıåĴĮ
    -0.25
    åħ¶ä»ĸ
    -0.25
    åĴĮåľ°åĮº
    -0.24
    POSITIVE LOGITS
    /or
    0.36
    /OR
    0.28
    eres
    0.24
    maybe
    0.24
    vil
    0.24
     maybe
    0.23
    Maybe
    0.21
    èµ°äºĨ
    0.21
     hence
    0.21
     thus
    0.21
    Activations Density 0.168%

    No Known Activations