© 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. 1883
    Prev
    Next
    INDEX
    Explanations

    wide-angle, landscape, scope

    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
     Called
    -0.23
    ä¸įæľį
    -0.22
    .elem
    -0.22
    RLF
    -0.22
    icho
    -0.22
    .cum
    -0.21
    .clock
    -0.20
    umped
    -0.20
    edis
    -0.20
    âĦ¡
    -0.20
    POSITIVE LOGITS
    /full
    0.31
    ness
    0.27
     enough
    0.27
    çīĪ
    0.26
    å¹ķ
    0.26
    -format
    0.24
    æ¯Ķä¾ĭ
    0.23
    è²Į
    0.23
    æĸľ
    0.23
    çĬ¶æĢģä¸ĭ
    0.23
    Activations Density 0.002%

    No Known Activations