© 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. 2855
    Prev
    Next
    INDEX
    Explanations

    etymology or sync

    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
    cies
    -0.25
    è¥Ħéĺ³
    -0.23
    ,['
    -0.23
    InThe
    -0.22
    odem
    -0.21
    æ±´
    -0.21
    _PCIE
    -0.21
     Contract
    -0.21
    roph
    -0.21
    rita
    -0.21
    POSITIVE LOGITS
    骡
    0.27
    bedo
    0.26
    ationally
    0.25
    sters
    0.25
    ç°ĩ
    0.24
    bounce
    0.24
     USAGE
    0.23
    undo
    0.23
    WORDS
    0.22
    -links
    0.22
    Activations Density 0.003%

    No Known Activations