© 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. 2179
    Prev
    Next
    INDEX
    Explanations

    probability questions

    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
    guarded
    -0.23
    Å©
    -0.23
     fences
    -0.23
     fence
    -0.23
    ongan
    -0.21
    çĬ¶åħĥ
    -0.20
     desired
    -0.20
    就好äºĨ
    -0.20
     sling
    -0.20
    BuilderFactory
    -0.20
    POSITIVE LOGITS
     Cover
    0.26
    edBy
    0.26
    rupt
    0.25
    tel
    0.25
    Film
    0.24
     Patt
    0.24
    covering
    0.23
    oda
    0.23
    çĿ¡åīį
    0.23
    ç»Łè®¡
    0.22
    Activations Density 0.001%

    No Known Activations