© 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. 922
    Prev
    Next
    INDEX
    Explanations

    binding or bind

    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
    bject
    -0.22
    -reaching
    -0.22
    ledge
    -0.21
    mie
    -0.21
    ffective
    -0.21
    eur
    -0.20
    cean
    -0.19
    ein
    -0.19
    imson
    -0.19
    lement
    -0.18
    POSITIVE LOGITS
    еÑģп
    0.20
    hurst
    0.20
    chaft
    0.19
    atura
    0.19
    åĽ½å®ī
    0.19
    .getRoot
    0.19
    纽带
    0.19
    еÑģÑĤи
    0.18
    dings
    0.18
    ierte
    0.18
    Activations Density 0.028%

    No Known Activations