© 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. 15
    Prev
    Next
    INDEX
    Explanations

    xml attribute values

    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
     Grim
    -0.28
     never
    -0.26
    never
    -0.25
     sca
    -0.24
     stash
    -0.23
    ëıĮ
    -0.23
    OSE
    -0.23
    민
    -0.22
    Pose
    -0.22
    SSI
    -0.22
    POSITIVE LOGITS
     sentence
    0.26
    irk
    0.24
    sentence
    0.24
     Brake
    0.23
    orough
    0.23
    ÂŃi
    0.22
    =train
    0.22
     Urdu
    0.22
     formulation
    0.22
    reten
    0.22
    Activations Density 0.056%

    No Known Activations