© 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. 2789
    Prev
    Next
    INDEX
    Explanations

    taxa containing 'ch' or 'on'

    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
    OTE
    -0.24
     vote
    -0.23
     ir
    -0.22
    индив
    -0.22
    ungle
    -0.21
    -hover
    -0.21
    ãĥŃãĥ¼
    -0.21
     fab
    -0.21
     OM
    -0.21
    PIP
    -0.21
    POSITIVE LOGITS
    abl
    0.26
    è¹Ń
    0.25
    inq
    0.23
    atri
    0.23
    ut
    0.23
    æѦåĻ¨
    0.23
    olg
    0.23
    ede
    0.22
    inct
    0.22
    sonian
    0.21
    Activations Density 0.226%

    No Known Activations