© 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. 2895
    Prev
    Next
    INDEX
    Explanations

    reinstall, repair, restore, fit, back

    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
    é©°
    -0.25
     concession
    -0.24
    å¿ħå®ļ
    -0.24
     Scalar
    -0.24
     dissoci
    -0.24
    Border
    -0.23
     concessions
    -0.23
    åİī害
    -0.23
     Border
    -0.22
     Grund
    -0.22
    POSITIVE LOGITS
     restore
    0.34
    /install
    0.33
     restored
    0.33
     restoring
    0.33
    	restore
    0.32
    å®īè£ħ
    0.31
    restore
    0.31
     restoration
    0.30
     reinstall
    0.29
     restores
    0.29
    Activations Density 0.034%

    No Known Activations