© 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. 679
    Prev
    Next
    INDEX
    Explanations

    respondents in surveys

    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
    åľ°å¸¦
    -0.20
    bur
    -0.20
    tures
    -0.19
    bid
    -0.19
    wards
    -0.18
    mith
    -0.18
    åŁ¹åħ»åѦçĶŁ
    -0.18
    lest
    -0.18
    burst
    -0.18
     exponent
    -0.18
    POSITIVE LOGITS
    urai
    0.22
    sWith
    0.22
    uren
    0.21
    ree
    0.19
    éĤ®ç®±
    0.19
    té
    0.19
    inate
    0.18
    ience
    0.18
    èĢħçļĦ
    0.18
    åĽŀçŃĶ
    0.18
    Activations Density 0.015%

    No Known Activations