© 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. 2152
    Prev
    Next
    INDEX
    Explanations

    Settings, edit, tools, file, preferences

    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
    said
    -0.24
    overrides
    -0.24
    第ä¸ĢæŶéĹ´
    -0.23
    imei
    -0.22
    çĤī
    -0.22
    opp
    -0.22
    +","+
    -0.22
    addy
    -0.22
    skin
    -0.21
    çļĦäºĭå®ŀ
    -0.21
    POSITIVE LOGITS
    åĨįåĪ°
    0.28
     Settings
    0.25
     ..↵↵
    0.25
    ä¸ĭçļĦ
    0.25
     cob
    0.24
     folders
    0.23
    _EXPORT
    0.23
    urat
    0.22
     choose
    0.22
     tertiary
    0.22
    Activations Density 0.061%

    No Known Activations