© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-8B
    5. 18-RESID-BATCHTOPK-65K__L0-80
    7. 1692
    Prev
    Next
    INDEX
    Explanations

    spatial distribution and patterns

    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
    assage
    -0.25
    rium
    -0.24
    åĨĴ
    -0.23
     Clothes
    -0.23
     reducers
    -0.22
    /session
    -0.22
    agog
    -0.21
    交æį¢
    -0.21
    trash
    -0.21
    æı©
    -0.21
    POSITIVE LOGITS
    åĪĨå¸ĥ
    0.50
    åľ°åĽ¾
    0.48
     distribution
    0.47
    åĽ¾æ¡Ī
    0.47
     map
    0.46
     maps
    0.45
     regions
    0.45
     patterns
    0.43
     geographical
    0.42
     spatial
    0.42
    Activations Density 0.212%

    No Known Activations