© 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. 2076
    Prev
    Next
    INDEX
    Explanations

    another person or thing

    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
    inan
    -0.26
     \@
    -0.24
    é©°
    -0.23
    åĪ©çĶ¨
    -0.23
     prize
    -0.23
     Fellow
    -0.22
     fet
    -0.22
    åħĭèݱ
    -0.22
    stral
    -0.22
    èĩ¼
    -0.21
    POSITIVE LOGITS
    generic
    0.23
    æĪijè§īå¾Ĺ
    0.23
     ropes
    0.23
    &e
    0.22
     Grocery
    0.22
     Moments
    0.21
     anders
    0.20
    èĥ½ä½¿
    0.20
     Psych
    0.20
    Mom
    0.20
    Activations Density 0.051%

    No Known Activations