© 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. 464
    Prev
    Next
    INDEX
    Explanations

    intracellular, articular, parasites

    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
    aul
    -0.27
    apel
    -0.26
    ilos
    -0.24
    -ball
    -0.22
    CTS
    -0.21
    å¾·å°Ķ
    -0.21
    amb
    -0.21
    ìĸ´
    -0.21
    kind
    -0.21
    tol
    -0.20
    POSITIVE LOGITS
    ities
    0.33
    ucks
    0.25
    ITIES
    0.25
    ity
    0.23
    ITY
    0.22
    æĴŃ
    0.22
    icators
    0.22
    æĪĸå¤ļ
    0.21
    fax
    0.21
    otropic
    0.21
    Activations Density 0.182%

    No Known Activations