© 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. 555
    Prev
    Next
    INDEX
    Explanations

    military ranks and titles

    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
    olson
    -0.27
     spill
    -0.24
    çĽijæµĭ
    -0.24
     Inputs
    -0.23
    èĩŃ
    -0.23
    æ£Ģæµĭ
    -0.23
    å®īæ£Ģ
    -0.23
    æįķæįī
    -0.22
    uforia
    -0.22
     champs
    -0.22
    POSITIVE LOGITS
    级åĪ«
    0.57
    èģĮ称
    0.43
    级åĪ«çļĦ
    0.42
    è¡Ķ
    0.41
    称åı·
    0.41
    èģĮåĬ¡
    0.39
    çŃī级
    0.38
    äºĮ级
    0.37
    ä¸ī级
    0.37
    æĻĭåįĩ
    0.36
    Activations Density 0.093%

    No Known Activations