© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-8B
    5. 18-RESID-BATCHTOPK-65K__L0-80
    7. 1119
    Prev
    Next
    INDEX
    Explanations

    flag, wrapping, quality, broken, rotation, immature, google, mature, clean

    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
     Transfer
    -0.22
    Transfer
    -0.22
    tx
    -0.22
    озд
    -0.22
    IOD
    -0.22
     микÑĢо
    -0.21
     skÅĤad
    -0.21
    kit
    -0.21
    éĥ¨
    -0.21
    .mag
    -0.21
    POSITIVE LOGITS
     thereof
    0.28
     ones
    0.24
    /null
    0.24
    rack
    0.23
    ä¸İåıijå±ķ
    0.23
    chè
    0.23
    abl
    0.23
    edException
    0.23
    /exec
    0.23
    è¡·
    0.22
    Activations Density 0.607%

    No Known Activations