© 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. 1676
    Prev
    Next
    INDEX
    Explanations

    head followed by direction

    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
    iad
    -0.19
    asjon
    -0.19
    HttpClient
    -0.18
    æ·±åİļçļĦ
    -0.18
    há»ı
    -0.17
    unde
    -0.17
    åIJĪçIJĨçļĦ
    -0.17
    otton
    -0.17
    iew
    -0.17
    horizontal
    -0.17
    POSITIVE LOGITS
    edly
    0.30
    quarters
    0.29
    gear
    0.25
    lights
    0.23
    OwnProperty
    0.23
    uates
    0.23
    orses
    0.22
    ings
    0.22
    dings
    0.22
    çĤ³
    0.22
    Activations Density 0.068%

    No Known Activations