© 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. 1295
    Prev
    Next
    INDEX
    Explanations

    covered by

    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
     impossible
    -0.25
    ä¸ĢåĪĩéĥ½
    -0.23
    åıªä¸º
    -0.22
    hoe
    -0.22
    ä¸ĢåĪĩ
    -0.22
     Impossible
    -0.22
     everything
    -0.22
    Impossible
    -0.21
     imposs
    -0.21
    shapes
    -0.21
    POSITIVE LOGITS
     coverage
    0.27
     hindsight
    0.24
     TAR
    0.23
     radar
    0.23
     unserer
    0.22
     suk
    0.22
     Clair
    0.22
    ä¾ĭå¤ĸ
    0.21
     descriptive
    0.21
     Coverage
    0.21
    Activations Density 0.045%

    No Known Activations