© 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. 2997
    Prev
    Next
    INDEX
    Explanations

    evaluation 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
    /her
    -0.20
    ï¸ı
    -0.20
    »¿
    -0.19
    lines
    -0.19
    away
    -0.19
    zap
    -0.18
    à¸ĩ
    -0.18
    ago
    -0.18
    elastic
    -0.17
    ler
    -0.17
    POSITIVE LOGITS
    uator
    0.30
    äºĨä¸Ģä¸ĭ
    0.28
    uable
    0.27
    uated
    0.27
    ByPrimaryKey
    0.23
    uating
    0.23
    ä¸Ģä¸ĭ
    0.23
    /control
    0.22
    åĴĮåıijå±ķ
    0.22
    ments
    0.21
    Activations Density 0.086%

    No Known Activations