© 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. 638
    Prev
    Next
    INDEX
    Explanations

    IP addresses and network addresses

    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
    汶
    -0.25
    lle
    -0.23
     yaml
    -0.22
     Glyph
    -0.22
    ysi
    -0.21
    _yaml
    -0.21
    ailable
    -0.21
     lle
    -0.21
    gli
    -0.21
     Abort
    -0.20
    POSITIVE LOGITS
    èĩªå¦Ĥ
    0.23
     unsus
    0.22
     Sunrise
    0.22
    å½ĵçĦ¶æĺ¯
    0.21
    łģ
    0.21
     McM
    0.21
    until
    0.21
    å½ĵçĦ¶
    0.20
     Sunset
    0.20
    numeric
    0.20
    Activations Density 0.009%

    No Known Activations