© 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. 1208
    Prev
    Next
    INDEX
    Explanations

    self-reference and reflexive pronouns

    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
    acer
    -0.25
    ham
    -0.25
    ocos
    -0.23
    bih
    -0.23
    clr
    -0.22
     thuyết
    -0.21
     depos
    -0.21
    _hdl
    -0.21
     Nearby
    -0.21
    à¤ł
    -0.21
    POSITIVE LOGITS
    让èĩªå·±
    0.42
     selves
    0.41
    /self
    0.39
    self
    0.38
     ÑģебÑı
    0.36
    (Self
    0.35
     oneself
    0.34
    Self
    0.33
     self
    0.33
    _self
    0.33
    Activations Density 0.048%

    No Known Activations