© 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. 2584
    Prev
    Next
    INDEX
    Explanations

    technical design and systems

    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
    çĦī
    -0.27
    è´¨éĩıåĴĮ
    -0.25
    raid
    -0.23
    Sc
    -0.22
    esa
    -0.22
    sam
    -0.21
    Cas
    -0.21
     PI
    -0.21
    enas
    -0.21
    çĺª
    -0.20
    POSITIVE LOGITS
     Berger
    0.23
    çļĦåĮºåĪ«
    0.22
    çŃīåIJĦç§į
    0.21
    æł¾
    0.21
    ingleton
    0.20
    éĥ½å¾Ī
    0.20
    åģļçļĦäºĭæĥħ
    0.20
     rv
    0.20
     isEmpty
    0.20
    æŁ´
    0.20
    Activations Density 0.664%

    No Known Activations