© 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. 2588
    Prev
    Next
    INDEX
    Explanations

    ordinance, ordained

    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
    -ever
    -0.21
    äºijéĽĨ
    -0.20
    ä¸įæĩĪ
    -0.20
    itzer
    -0.20
    urv
    -0.19
    ischer
    -0.19
    owed
    -0.19
    ãĥĪãĥ«
    -0.19
     ------------------------------------------------------------------------↵
    -0.19
    erg
    -0.18
    POSITIVE LOGITS
     vitae
    0.25
    ality
    0.22
    éŨåīį
    0.22
    inals
    0.21
    gebung
    0.20
    ation
    0.20
    çĶŁäº§æĢ»åĢ¼
    0.20
    /method
    0.20
    ulation
    0.19
    antal
    0.19
    Activations Density 0.007%

    No Known Activations