© 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. 51
    Prev
    Next
    INDEX
    Explanations

    'in' followed by '

    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
    ön
    -0.23
    UGE
    -0.20
    arah
    -0.20
    kıl
    -0.20
    IPH
    -0.20
    krÄĻc
    -0.19
    URN
    -0.19
    riet
    -0.19
    IBLE
    -0.19
    iming
    -0.19
    POSITIVE LOGITS
    Ùĭ
    0.30
    ly
    0.27
    /up
    0.25
    麽
    0.25
    /rem
    0.25
    /her
    0.24
    r
    0.23
    wards
    0.23
    ÂĢÂĻ
    0.23
    éĴ
    0.23
    Activations Density 0.013%

    No Known Activations