© 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. 2480
    Prev
    Next
    INDEX
    Explanations

    no longer

    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
    onor
    -0.23
    ories
    -0.21
    reeze
    -0.21
    ors
    -0.20
    ings
    -0.20
     mù
    -0.19
    ened
    -0.19
    arResult
    -0.19
     amounts
    -0.18
    åIJĦå¼Ĥ
    -0.18
    POSITIVE LOGITS
    adays
    0.26
    theless
    0.23
    oha
    0.22
    days
    0.22
    çīĩåŃIJ
    0.21
    fter
    0.20
    zt
    0.20
    locker
    0.20
    zej
    0.20
    说æĺ¯
    0.20
    Activations Density 0.004%

    No Known Activations