© 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. 2929
    Prev
    Next
    INDEX
    Explanations

    building features and location

    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
    éģ¨
    -0.28
    OOT
    -0.26
    äºĮ代
    -0.25
    游
    -0.25
    guide
    -0.24
     Guides
    -0.24
    å¿ĥè¡Ģ
    -0.24
     Rough
    -0.24
    éĿ´
    -0.23
     Destination
    -0.23
    POSITIVE LOGITS
    ä½įç½®
    0.28
    å¸ĥå±Ģ
    0.27
     disadvantages
    0.27
    éĢļé£İ
    0.26
     advantageous
    0.26
     exterior
    0.26
     disadvantage
    0.26
     góc
    0.25
    æī¹æ¬¡
    0.25
    -facing
    0.25
    Activations Density 0.042%

    No Known Activations