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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-8B
    5. 18-RESID-BATCHTOPK-65K__L0-80
    7. 2940
    Prev
    Next
    INDEX
    Explanations

    then followed by an event or action

    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
    оÑĢо
    -0.24
    å±ĬæŶ
    -0.23
     Ness
    -0.22
    /from
    -0.22
    TRGL
    -0.21
     component
    -0.21
    SURE
    -0.21
    å¦Ĥæŀľ
    -0.21
     Notebook
    -0.21
    reten
    -0.20
    POSITIVE LOGITS
    åıĪ被
    0.24
    èĢ»
    0.24
    pole
    0.24
    ÑĥÑģÑĤ
    0.24
    ivre
    0.24
    niest
    0.24
    moon
    0.23
    eph
    0.23
    inf
    0.23
    -second
    0.23
    Activations Density 0.023%

    No Known Activations