© 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. 1990
    Prev
    Next
    INDEX
    Explanations

    implied warranty

    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
    _MARKER
    -0.23
     hospitalized
    -0.23
    hood
    -0.23
     bean
    -0.21
     Concat
    -0.21
    ież
    -0.21
    Uuid
    -0.20
    éĹ®æĪij
    -0.20
    _concat
    -0.20
    èį
    -0.20
    POSITIVE LOGITS
    mouth
    0.26
    岩
    0.22
    orp
    0.22
    Ñĥг
    0.21
    corp
    0.21
     companies
    0.21
    Č↵
    0.21
    orption
    0.21
    豫
    0.21
     cliffs
    0.20
    Activations Density 0.008%

    No Known Activations