© 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. 11
    Prev
    Next
    INDEX
    Explanations

    license

    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
    liest
    -0.23
     entire
    -0.23
    cho
    -0.23
    ç¨į
    -0.23
    oke
    -0.22
    highest
    -0.22
    smith
    -0.22
     highest
    -0.22
    	tab
    -0.21
    TypeName
    -0.21
    POSITIVE LOGITS
     pudd
    0.27
    antan
    0.24
    inate
    0.23
     lokal
    0.23
    _Stream
    0.23
     others
    0.22
    å¹²äºĭ
    0.22
     Loved
    0.22
    others
    0.22
     fing
    0.22
    Activations Density 0.497%

    No Known Activations