© 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. 1527
    Prev
    Next
    INDEX
    Explanations

    recreate recipes

    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
    adients
    -0.22
    Advisor
    -0.21
     profit
    -0.21
    roker
    -0.21
    orne
    -0.21
    rollable
    -0.21
     gain
    -0.21
    vero
    -0.21
    inity
    -0.21
    ect
    -0.20
    POSITIVE LOGITS
    uras
    0.26
    æ¿ĢçĥĪ
    0.24
     Tart
    0.24
     footage
    0.24
    åıijçĶŁåľ¨
    0.24
    Danger
    0.23
    ä¸Ģä¸ĭ
    0.23
    çĮĽçĥĪ
    0.23
    oes
    0.23
     Franken
    0.23
    Activations Density 0.002%

    No Known Activations