© 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. 2896
    Prev
    Next
    INDEX
    Explanations

    true or false

    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
    åīįä¸ĸ
    -0.26
    è¿ĩåİ»
    -0.25
    erez
    -0.25
     Mur
    -0.25
    ($__
    -0.24
    Mur
    -0.23
    åıijå±ķ空éĹ´
    -0.23
    CreateTime
    -0.23
    ystate
    -0.23
    (counter
    -0.23
    POSITIVE LOGITS
     loser
    0.25
    表æĢģ
    0.25
     AttributeError
    0.24
     Statements
    0.24
     terse
    0.24
    ä¸įåħģ许
    0.24
     euth
    0.23
     gib
    0.23
    .Exit
    0.23
    è´¥
    0.23
    Activations Density 0.009%

    No Known Activations