© 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. 826
    Prev
    Next
    INDEX
    Explanations

    test or testing

    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
    hand
    -0.28
    hit
    -0.25
    hits
    -0.24
    hunt
    -0.24
    him
    -0.24
    halt
    -0.23
    hot
    -0.22
    holder
    -0.22
    arden
    -0.22
    ho
    -0.21
    POSITIVE LOGITS
    ting
    0.66
    ted
    0.50
    ypes
    0.47
    ype
    0.44
    TING
    0.42
    ools
    0.41
    ters
    0.40
    tings
    0.39
    tle
    0.39
    inerary
    0.38
    Activations Density 2.599%

    No Known Activations