© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-8B
    5. 18-RESID-BATCHTOPK-65K__L0-80
    7. 589
    Prev
    Next
    INDEX
    Explanations

    version or normal

    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
    feb
    -0.23
     Maur
    -0.23
    è·µ
    -0.22
    æľīå¾ħ
    -0.22
     DC
    -0.22
    ce
    -0.22
    cec
    -0.22
     Ne
    -0.22
    æķĻä½ł
    -0.22
    ulo
    -0.21
    POSITIVE LOGITS
    iento
    0.26
     versus
    0.24
     groom
    0.24
    ilename
    0.24
    infer
    0.23
    nov
    0.23
     vs
    0.23
    èĢĮéĿŀ
    0.23
     lẫn
    0.22
     Edison
    0.22
    Activations Density 0.204%

    No Known Activations