© 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. 2342
    Prev
    Next
    INDEX
    Explanations

    puzzles and names

    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
    ussions
    -0.30
    adas
    -0.27
    uff
    -0.25
    bserv
    -0.25
    assel
    -0.25
    anja
    -0.25
    cff
    -0.24
    .uf
    -0.24
     rehabilit
    -0.24
    sic
    -0.23
    POSITIVE LOGITS
     clue
    0.39
     crossword
    0.34
     tricky
    0.33
     clues
    0.32
    çŃĶæ¡Ī
    0.30
    线索
    0.30
     alphabetical
    0.30
    çļĦçŃĶæ¡Ī
    0.29
    è¯į
    0.29
     trick
    0.29
    Activations Density 0.052%

    No Known Activations