© 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. 673
    Prev
    Next
    INDEX
    Explanations

    region

    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
    ðŁı»
    -0.29
    çĦ¶æĺ¯
    -0.21
     viá»ĩc
    -0.20
    ðŁı¼
    -0.20
     majority
    -0.19
    ../
    -0.19
    å±ĢéĿ¢
    -0.19
     routine
    -0.18
    cec
    -0.18
     realizado
    -0.18
    POSITIVE LOGITS
    ally
    0.46
    nement
    0.31
    nable
    0.30
    åŁ
    0.28
    naire
    0.28
    ality
    0.28
    åĨħçļĦ
    0.28
    ials
    0.27
    çĶŁäº§æĢ»åĢ¼
    0.26
    wide
    0.25
    Activations Density 0.034%

    No Known Activations