© 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. 2163
    Prev
    Next
    INDEX
    Explanations

    as if

    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
    otec
    -0.27
    æĨ§
    -0.24
    éħ®
    -0.24
    èıĸ
    -0.23
     puls
    -0.23
     Forward
    -0.22
    ç¼ħ
    -0.22
    èĤĦ
    -0.21
     compar
    -0.21
     Ot
    -0.21
    POSITIVE LOGITS
    åıijçİ°äºĨ
    0.25
    åıijçİ°
    0.25
    mask
    0.24
    alerts
    0.24
    _SUR
    0.23
    omatic
    0.23
    ysi
    0.23
     Isles
    0.23
    éĶĻè¿ĩäºĨ
    0.23
    çĻ¼çı¾
    0.23
    Activations Density 0.020%

    No Known Activations