© 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. 2820
    Prev
    Next
    INDEX
    Explanations

    elongated vowels with exclamation!

    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
    ä¹ĭæĺŁ
    -0.28
    第äºĮæī¹
    -0.25
    äºĮåŃĹ
    -0.25
    第ä¸Ģæī¹
    -0.25
    ä¸Ģæī¹
    -0.24
    cname
    -0.23
    æĺ¯éĿŀ
    -0.22
    äºĨä¸Ģæī¹
    -0.22
    æĺİçıł
    -0.21
    æĢ§å¼º
    -0.20
    POSITIVE LOGITS
    hw
    0.24
    !!,
    0.24
    /video
    0.23
    -refresh
    0.21
    !
    0.21
    plier
    0.21
    hic
    0.21
    lek
    0.21
    rello
    0.20
    -git
    0.20
    Activations Density 0.021%

    No Known Activations