© 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. 2403
    Prev
    Next
    INDEX
    Explanations

    MTV and related media

    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
     McA
    -0.25
    rection
    -0.24
    andal
    -0.23
     fung
    -0.21
     irrigation
    -0.21
     Episodes
    -0.21
    king
    -0.21
    ió
    -0.20
    èĥ½åĬĽå¼º
    -0.20
    Processes
    -0.20
    POSITIVE LOGITS
    å¢Ļ
    0.25
    社
    0.23
    导åIJij
    0.23
    /***/
    0.21
    braska
    0.20
    æ¼ı
    0.20
    é¾Ī
    0.20
    .big
    0.20
    _WALL
    0.20
    å·¥å§Ķ
    0.20
    Activations Density 0.002%

    No Known Activations