© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-8B
    5. 18-RESID-BATCHTOPK-65K__L0-80
    7. 3032
    Prev
    Next
    INDEX
    Explanations

    animation and animate

    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
    ña
    -0.22
    lean
    -0.20
    edException
    -0.19
    å¿ħè¦ģçļĦ
    -0.18
    ness
    -0.18
    xic
    -0.18
    iness
    -0.18
    ive
    -0.18
    skin
    -0.18
    ver
    -0.17
    POSITIVE LOGITS
    asjon
    0.23
    /photo
    0.20
    ously
    0.20
    ãģĹãģ¾ãģĨ
    0.20
    stu
    0.20
    ãĥ¼ãĤ·ãĥ§ãĥ³
    0.19
    /ec
    0.19
     apocalypse
    0.19
     Pavel
    0.19
    osity
    0.19
    Activations Density 0.018%

    No Known Activations