© 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. 2016
    Prev
    Next
    INDEX
    Explanations

    or so

    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
    ä¸įäºĨ
    -0.26
    /process
    -0.25
    eer
    -0.24
    ivity
    -0.23
    åĴĮ个人
    -0.22
    igue
    -0.22
    holm
    -0.22
    ry
    -0.22
    soever
    -0.22
    æĻ°
    -0.22
    POSITIVE LOGITS
    (NS
    0.23
    à¸Ĥà¸Ńà¸ĩà¸ģาร
    0.23
    erti
    0.21
    çļĦæŶéĹ´éĩĮ
    0.21
    _THAT
    0.20
    çļĦåıijå±ķ
    0.19
    erset
    0.19
    ãĤĴ缮
    0.19
    eref
    0.19
    .Exec
    0.19
    Activations Density 0.017%

    No Known Activations