© 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. 1233
    Prev
    Next
    INDEX
    Explanations

    routes and file paths

    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
    mPid
    -0.33
    .didReceiveMemoryWarning
    -0.32
    THOOK
    -0.30
    gMaps
    -0.30
    "urls
    -0.28
    :UIControl
    -0.28
    (grammarAccess
    -0.28
    DECREF
    -0.27
    FunctionFlags
    -0.27
    'gc
    -0.27
    POSITIVE LOGITS
    è¿Ļ个åIJįåŃĹ
    0.36
    done
    0.27
    Calc
    0.27
    çļ¤
    0.27
    calc
    0.26
    Test
    0.26
    éĢĻåĢĭ
    0.26
    è¿Ļ个è¯į
    0.25
     <->
    0.24
    äºĮåŃĹ
    0.24
    Activations Density 0.856%

    No Known Activations