© 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. 2275
    Prev
    Next
    INDEX
    Explanations

    characters, symbols, and unicode

    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
    ä¸Ģ家
    -0.28
    ramework
    -0.26
    sonian
    -0.26
    Plans
    -0.25
    Videos
    -0.25
    plans
    -0.24
    翻身
    -0.24
     slam
    -0.23
     newObj
    -0.23
    .endTime
    -0.23
    POSITIVE LOGITS
     characters
    0.48
    åŃĹ符
    0.47
     alphanumeric
    0.40
    ASCII
    0.39
     Characters
    0.38
     Unicode
    0.38
    _unicode
    0.35
     caracteres
    0.35
    characters
    0.34
     ASCII
    0.34
    Activations Density 0.097%

    No Known Activations