© 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. 2298
    Prev
    Next
    INDEX
    Explanations

    python function definitions

    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
    -liter
    -0.28
    –
    -0.25
    -sensitive
    -0.23
    -material
    -0.23
    Anthony
    -0.23
    arring
    -0.23
    -lib
    -0.23
    -worthy
    -0.22
    -related
    -0.22
    zie
    -0.22
    POSITIVE LOGITS
     ÐŁÐ¾Ñĩем
    0.34
    индивид
    0.32
    индив
    0.31
     _(
    0.27
    еÑģÑĤеÑģÑĤвенн
    0.27
    EDURE
    0.26
    пÑĢоÑĦеÑģÑģионал
    0.25
    棽
    0.24
    åĨįåĪ°
    0.24
    há»ķ
    0.24
    Activations Density 0.266%

    No Known Activations