© 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. 1362
    Prev
    Next
    INDEX
    Explanations

    pre-existing / underlying

    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
    -0.26
    æŀ¯çĩ¥
    -0.24
    ahas
    -0.22
    åıĸ
    -0.22
    å±ı
    -0.22
    -half
    -0.21
     Lid
    -0.21
    apos
    -0.21
     inspired
    -0.21
    /she
    -0.21
    POSITIVE LOGITS
    Formats
    0.23
    è´Łæĭħ
    0.23
    waters
    0.22
    mmc
    0.22
    ivities
    0.22
    FL
    0.21
    çĹķ
    0.21
    çłľ
    0.21
    ibilities
    0.21
    arian
    0.21
    Activations Density 0.001%

    No Known Activations