© 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. 1865
    Prev
    Next
    INDEX
    Explanations

    sign language, morse code

    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
    æIJŀ
    -0.26
    é¦ħ
    -0.25
     Dirt
    -0.25
     Boss
    -0.25
    ammu
    -0.24
     offending
    -0.23
    ptype
    -0.23
     ÑģеÑĢии
    -0.23
    hue
    -0.23
     %.
    -0.22
    POSITIVE LOGITS
    èģĭ
    0.33
    è¯Ń
    0.32
    èªŀ
    0.31
     deaf
    0.30
    æīĭåĬ¿
    0.29
    è¯Ńè¨Ģ
    0.28
    æĹłå£°
    0.27
    èŃ
    0.27
    æĻ®éĢļè¯Ŀ
    0.27
    åĨįçĶŁ
    0.26
    Activations Density 0.008%

    No Known Activations