© 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. 422
    Prev
    Next
    INDEX
    Explanations

    numbers and punctuation, e.g. `08/705,043`

    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
    åĩ¸
    -0.28
     Conv
    -0.24
     reap
    -0.23
    gett
    -0.22
    .pp
    -0.22
    ç¿Ĭ
    -0.21
    ä¾Ľ
    -0.21
    ç¢į
    -0.21
    (Response
    -0.21
    è£ģ
    -0.21
    POSITIVE LOGITS
     Voy
    0.24
    eu
    0.23
    EA
    0.22
     Furious
    0.21
    ARY
    0.21
     film
    0.20
    tte
    0.20
    e
    0.20
    èĹĿ
    0.20
    åħ¨æĹ¥
    0.20
    Activations Density 0.001%

    No Known Activations