© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-8B
    5. 18-RESID-BATCHTOPK-65K__L0-80
    7. 376
    Prev
    Next
    INDEX
    Explanations

    inside scoop or access

    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
    èįīæ¡Ī
    -0.23
    ç³Ĭ
    -0.23
    åŁºæķ°
    -0.23
    nota
    -0.23
    æķijåij½
    -0.22
    åĽ¾æ¡Ī
    -0.22
     categor
    -0.22
    ishment
    -0.22
    ensed
    -0.21
     conformity
    -0.21
    POSITIVE LOGITS
     insider
    0.42
     privileged
    0.40
     insight
    0.38
     insiders
    0.38
     access
    0.36
    .access
    0.35
     Insider
    0.35
    åĨħå¹ķ
    0.35
     insights
    0.35
     acceso
    0.33
    Activations Density 0.034%

    No Known Activations