© 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. 2328
    Prev
    Next
    INDEX
    Explanations

    issue number volume

    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
    å²ģæŶ
    -0.24
     fig
    -0.22
     centrif
    -0.22
     transporter
    -0.22
    -multi
    -0.21
    ijľ
    -0.21
     figure
    -0.21
    æľ
    -0.21
    è·³èĪŀ
    -0.21
    EMALE
    -0.21
    POSITIVE LOGITS
     Shoe
    0.27
    缮
    0.24
    ä¸ĵé¢ĺ
    0.24
     Journalism
    0.23
    cord
    0.23
     #:
    0.23
    undo
    0.23
     broadcasting
    0.23
    çīĪæĿĥæīĢæľī
    0.22
    headline
    0.22
    Activations Density 0.040%

    No Known Activations