© 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. 1953
    Prev
    Next
    INDEX
    Explanations

    Kansas City

    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
     König
    -0.22
    stown
    -0.22
     Christie
    -0.21
    ège
    -0.21
    quo
    -0.21
    æ¡Ħ
    -0.21
    orate
    -0.20
    Ñĥз
    -0.20
    uet
    -0.20
    ctor
    -0.19
    POSITIVE LOGITS
     loud
    0.21
    éĴ§
    0.21
    inker
    0.21
    å¿ĥåºķ
    0.20
    jni
    0.20
    ä¸Ģ人
    0.20
    /ns
    0.19
    going
    0.19
    åĵį
    0.19
     chop
    0.19
    Activations Density 0.006%

    No Known Activations