© 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. 2538
    Prev
    Next
    INDEX
    Explanations

    ball grid, ball retrieval, ball-shaped

    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
    LEM
    -0.22
     ÐIJлекÑģан
    -0.20
    eme
    -0.20
     vast
    -0.20
     Ñģами
    -0.19
    estr
    -0.19
    ¢åįķ
    -0.19
    ellig
    -0.19
    ably
    -0.18
     ÐŁÐ¾Ñĩем
    -0.18
    POSITIVE LOGITS
    ity
    0.37
    istics
    0.29
    er
    0.27
    fish
    0.27
    room
    0.27
    arity
    0.26
    istic
    0.25
    eria
    0.23
    iance
    0.23
    entine
    0.23
    Activations Density 0.028%

    No Known Activations