© 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. 2274
    Prev
    Next
    INDEX
    Explanations

    raw material

    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
    ially
    -0.26
    ials
    -0.24
    utter
    -0.24
    ately
    -0.23
     jams
    -0.23
    åģľçĶµ
    -0.22
    æĹ¥å¤ľ
    -0.22
    å¤ľéĹ´
    -0.22
    ialized
    -0.21
    å¤ľæĻļ
    -0.21
    POSITIVE LOGITS
    quisites
    0.22
    Replacement
    0.21
    itta
    0.21
    .Chat
    0.21
     unders
    0.20
     replacement
    0.20
    ä¸ŃåİŁ
    0.20
    æĨij
    0.20
    è¿ĻäºĽä¸ľè¥¿
    0.20
    foot
    0.19
    Activations Density 0.005%

    No Known Activations