© 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. 2914
    Prev
    Next
    INDEX
    Explanations

    names followed by surnames/initials

    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
    è¿Ļ件
    -0.26
    åħ·ä½ĵçļĦ
    -0.25
    æīĢæľīçļĦ
    -0.23
    è¿Ļ份
    -0.23
    flen
    -0.23
    éĢĻåĢĭ
    -0.23
     ÐŁÐ¾Ñĩем
    -0.22
    æ¯ı个
    -0.21
     vÃŃde
    -0.20
    è¿Ļ个åIJįåŃĹ
    -0.20
    POSITIVE LOGITS
    mont
    0.25
    -turned
    0.24
     McG
    0.23
    abb
    0.23
     hers
    0.22
    -design
    0.21
     bursting
    0.20
     zostaÅĤa
    0.20
     In
    0.20
    iano
    0.20
    Activations Density 0.125%

    No Known Activations