© 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. 1216
    Prev
    Next
    INDEX
    Explanations

    identifying patterns and trends

    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
     adrenaline
    -0.24
    Hung
    -0.24
    èijµ
    -0.24
    åħ¨ç¨ĭ
    -0.23
    è¦ģæ±Ĥ
    -0.23
    ::-
    -0.23
    orts
    -0.22
    åĬŁ
    -0.22
     weighs
    -0.22
    çݰ代åĮĸ
    -0.22
    POSITIVE LOGITS
     patterns
    0.59
     Patterns
    0.52
     trends
    0.52
    Patterns
    0.52
    patterns
    0.49
    è¶ĭåĬ¿
    0.46
    (pattern
    0.45
     pattern
    0.45
    _patterns
    0.45
    Pattern
    0.44
    Activations Density 0.206%

    No Known Activations