© 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. 415
    Prev
    Next
    INDEX
    Explanations

    focus on

    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
     Facing
    -0.24
     precinct
    -0.24
    è´±
    -0.23
    OfType
    -0.23
     firefighter
    -0.23
     feu
    -0.22
    æ¯Ķè¾ĥå¤ļ
    -0.22
    ç¦Ģ
    -0.21
    oven
    -0.21
     наÑĢко
    -0.21
    POSITIVE LOGITS
     contour
    0.33
     lenses
    0.30
     lens
    0.30
    éķľå¤´
    0.29
    è§Ĩ线
    0.26
     Cont
    0.26
    peed
    0.25
     zoom
    0.25
     slow
    0.25
     speed
    0.25
    Activations Density 0.016%

    No Known Activations