© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-8B
    5. 18-RESID-BATCHTOPK-65K__L0-80
    7. 386
    Prev
    Next
    INDEX
    Explanations

    hundreds of

    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
    gable
    -0.25
    ingly
    -0.24
    ä¸ĭä¸ĢæŃ¥
    -0.20
    unning
    -0.20
    outs
    -0.19
     обÑĢазом
    -0.19
    prefs
    -0.18
    cie
    -0.18
    ä¸įæĸŃå¢ŀ强
    -0.18
     háºŃu
    -0.18
    POSITIVE LOGITS
    acity
    0.24
    -long
    0.23
     thousand
    0.23
     ngÃłn
    0.23
    ä¸Ĭåįĥ
    0.22
     ÑĤÑĭÑģÑıÑĩ
    0.22
    iard
    0.22
    een
    0.21
    /or
    0.20
    iseconds
    0.20
    Activations Density 0.017%

    No Known Activations