© 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. 526
    Prev
    Next
    INDEX
    Explanations

    html tags and attributes

    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
    	namespace
    -0.31
    OfString
    -0.30
    ArrayType
    -0.29
    iationException
    -0.29
    Invariant
    -0.29
     Erotische
    -0.28
     nil
    -0.28
    Either
    -0.27
    éĽ»è©±åıĬ
    -0.27
    alars
    -0.27
    POSITIVE LOGITS
     Riders
    0.28
     Genre
    0.28
     spectacle
    0.28
     Drama
    0.28
     drama
    0.27
     Anthem
    0.26
     regrets
    0.26
    åł¤
    0.26
     Voll
    0.26
     créd
    0.25
    Activations Density 1.438%

    No Known Activations