© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-8B
    5. 18-RESID-BATCHTOPK-65K__L0-80
    7. 766
    Prev
    Next
    INDEX
    Explanations

    sweet sixteen, comment, cravings, melon, luxury, family, young, voice

    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
    usted
    -0.21
    ifold
    -0.20
     wealthy
    -0.20
    Ñīен
    -0.20
    ystem
    -0.19
    halt
    -0.19
    avier
    -0.18
    andler
    -0.18
    sweet
    -0.17
     Bris
    -0.17
    POSITIVE LOGITS
    ening
    0.40
    ened
    0.38
    -minded
    0.32
     enough
    0.30
    ness
    0.29
    ly
    0.25
    emente
    0.25
    (er
    0.25
    est
    0.25
    ities
    0.24
    Activations Density 0.005%

    No Known Activations