© 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. 1856
    Prev
    Next
    INDEX
    Explanations

    UPI and True indicators

    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
    retval
    -0.23
     anyway
    -0.22
    çĵ
    -0.22
    æ±½
    -0.22
     Liberty
    -0.22
    å½¢æĢģ
    -0.21
     siblings
    -0.21
     yet
    -0.21
     recognizable
    -0.20
    毫ä¸įçĬ¹è±«
    -0.20
    POSITIVE LOGITS
    _ascii
    0.26
    imap
    0.25
    请大家
    0.24
    chant
    0.24
    dish
    0.23
    lon
    0.22
    ADS
    0.22
    èĺijèıĩ
    0.22
    irate
    0.21
    ä¸įéĢĤåIJĪ
    0.21
    Activations Density 0.003%

    No Known Activations