© 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. 3011
    Prev
    Next
    INDEX
    Explanations

    configuration files

    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
     Sachs
    -0.23
    cido
    -0.23
    åıĪ好åıĪå¿«
    -0.22
    ÑĢÑı
    -0.21
    éĺŁéķ¿
    -0.21
    åºķå±Ĥ
    -0.21
     endpoint
    -0.21
    hands
    -0.20
    GROUND
    -0.20
    çĶµéĩı
    -0.20
    POSITIVE LOGITS
    ä¸ŃåIJ«æľī
    0.24
    æŶåĢĻ
    0.23
     prevail
    0.21
     Bolton
    0.21
    ÑģÑĤÑĥп
    0.21
    èĨº
    0.21
    ä¸Ńæľī
    0.21
    滿
    0.21
    chten
    0.20
    åĨł
    0.20
    Activations Density 0.158%

    No Known Activations