© 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. 32
    Prev
    Next
    INDEX
    Explanations

    dialogue

    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
    eral
    -0.22
    lake
    -0.20
    wards
    -0.20
    d
    -0.20
    rez
    -0.19
    idious
    -0.19
    dz
    -0.18
    cess
    -0.18
    coat
    -0.18
    rapper
    -0.18
    POSITIVE LOGITS
    ues
    0.26
    åĴĮæĶ¯æĮģ
    0.23
    gable
    0.22
    istic
    0.21
    buster
    0.21
    ative
    0.21
    ../
    0.20
     Ñģамого
    0.20
    æ¡Ĩ
    0.20
    ä¸įéĢļ
    0.19
    Activations Density 0.014%

    No Known Activations