© 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. 2917
    Prev
    Next
    INDEX
    Explanations

    Roger, Nigel, Ryan, Christophe

    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
    ãģĹãģ¾ãģĨ
    -0.22
    iliar
    -0.21
    itarian
    -0.21
    ality
    -0.20
    liness
    -0.20
    ors
    -0.20
    ities
    -0.19
    ally
    -0.19
    ious
    -0.19
    械
    -0.18
    POSITIVE LOGITS
    0.30
    tte
    0.18
     cus
    0.17
    {}]
    0.17
     gente
    0.17
    pio
    0.17
    Ø©
    0.17
    å¼ĢæĿ¥
    0.16
     formal
    0.16
    ×ķת
    0.16
    Activations Density 0.351%

    No Known Activations