© 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. 1401
    Prev
    Next
    INDEX
    Explanations

    percentage of cases

    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
    IFF
    -0.25
    顺åºĶ
    -0.24
    èĨľ
    -0.24
     Traffic
    -0.24
     capitals
    -0.23
    çľĭå¾ħ
    -0.23
    交éĢļ
    -0.23
     Memory
    -0.23
    æľŁåĨħ
    -0.23
    åĩĨå¤ĩ
    -0.22
    POSITIVE LOGITS
     cases
    0.39
    cases
    0.36
    Cases
    0.30
     Fälle
    0.29
     Cases
    0.28
    çĹħä¾ĭ
    0.27
     casos
    0.27
     clinically
    0.26
    normally
    0.26
     typically
    0.26
    Activations Density 0.242%

    No Known Activations