© 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. 2890
    Prev
    Next
    INDEX
    Explanations

    expand

    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
    hood
    -0.30
    INAL
    -0.22
    AMA
    -0.22
    ERAL
    -0.20
    chy
    -0.20
    OUN
    -0.19
    pins
    -0.19
    TING
    -0.19
    PAY
    -0.18
    аÑģÑĤ
    -0.18
    POSITIVE LOGITS
    ible
    0.30
    nist
    0.28
     StObject
    0.27
    /stretch
    0.26
    åĴĮå®ĮåĸĦ
    0.26
    äºĨèĩªå·±çļĦ
    0.26
    iture
    0.24
    /ref
    0.23
    ions
    0.22
    åݦ
    0.22
    Activations Density 0.034%

    No Known Activations