© 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. 1952
    Prev
    Next
    INDEX
    Explanations

    season year data

    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
    BODY
    -0.26
    éļıæŶéļıåľ°
    -0.25
     body
    -0.23
     eye
    -0.23
    eturn
    -0.22
    äºķ
    -0.21
    /feed
    -0.21
    ophage
    -0.21
    çIJĨ解åĴĮ
    -0.21
     chance
    -0.20
    POSITIVE LOGITS
     onwards
    0.31
    edition
    0.29
     onward
    0.26
    以æĿ¥
    0.26
    以ä¾Ĩ
    0.23
    ollipop
    0.22
    bull
    0.21
    تأسÙĬ
    0.21
    rd
    0.21
    entication
    0.21
    Activations Density 0.033%

    No Known Activations