© 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. 359
    Prev
    Next
    INDEX
    Explanations

    code syntax or paths

    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
    edException
    -0.23
    ç°ī
    -0.20
    çİĵ
    -0.19
    tas
    -0.19
    six
    -0.19
    nak
    -0.19
    笯
    -0.18
    dre
    -0.18
    disconnect
    -0.18
    çħŁ
    -0.18
    POSITIVE LOGITS
    IGINAL
    0.42
    ctrine
    0.38
    enticate
    0.35
    ftware
    0.33
    autiful
    0.33
    orary
    0.32
    cluded
    0.31
    finity
    0.31
    iversal
    0.31
    alytics
    0.30
    Activations Density 1.508%

    No Known Activations