© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-8B
    5. 18-RESID-BATCHTOPK-65K__L0-80
    7. 706
    Prev
    Next
    INDEX
    Explanations

    is [Month/DONE/India/Failed/T/New]

    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
     Âł Âł Âł Âł
    -0.23
    åľĥ
    -0.23
     lorem
    -0.22
    ç¼ł
    -0.22
    europäische
    -0.20
     tender
    -0.20
     kit
    -0.20
     Gerry
    -0.20
    anca
    -0.20
     üzerinden
    -0.20
    POSITIVE LOGITS
    oret
    0.32
     Www
    0.27
    neath
    0.27
    ’S
    0.26
    èĭ¥å¹²
    0.26
    'S
    0.25
     And
    0.25
    %E
    0.25
    åIJ¦
    0.24
    orem
    0.23
    Activations Density 1.016%

    No Known Activations