© 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. 1027
    Prev
    Next
    INDEX
    Explanations

    safari

    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
    rug
    -0.22
     Fukushima
    -0.22
    agem
    -0.21
    pile
    -0.20
    hips
    -0.20
    pyx
    -0.20
    -handed
    -0.20
    lec
    -0.18
    .sprite
    -0.18
    åĿĢ
    -0.18
    POSITIVE LOGITS
    ward
    0.22
    0.21
    çĶ¨åĵģ
    0.20
    ä¹IJåĽŃ
    0.20
    zug
    0.19
    анÑģ
    0.19
    -ready
    0.19
    ãģĭãģijãģ¦
    0.19
    -style
    0.19
    wards
    0.18
    Activations Density 0.003%

    No Known Activations