© 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. 792
    Prev
    Next
    INDEX
    Explanations

    Hong Kong

    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
    istic
    -0.22
    rhs
    -0.21
    tery
    -0.21
    ities
    -0.21
    nage
    -0.19
    uator
    -0.19
    iste
    -0.18
    åĺ¶
    -0.18
    aghan
    -0.18
    engu
    -0.18
    POSITIVE LOGITS
    sen
    0.22
    à¤
    0.21
    stad
    0.21
    agonal
    0.20
    è¯Ģ
    0.20
    evity
    0.20
    IMUM
    0.19
    Ĩµ
    0.18
    裳
    0.18
     Neg
    0.18
    Activations Density 0.005%

    No Known Activations