© 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. 1528
    Prev
    Next
    INDEX
    Explanations

    friend or foe

    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
     orderly
    -0.28
     Judiciary
    -0.28
     bureaucratic
    -0.28
     оÑĢган
    -0.27
     paperback
    -0.27
     judicial
    -0.27
     electoral
    -0.26
     ServiceProvider
    -0.26
     Electoral
    -0.26
    javax
    -0.26
    POSITIVE LOGITS
     adrenaline
    0.38
    ç«ŀæĬĢ
    0.36
    æĪ·å¤ĸ
    0.36
    éĩİå¤ĸ
    0.36
    éªijè¡Į
    0.35
     guys
    0.35
    åľºåľ°
    0.35
    éĢīæīĭ
    0.34
    éĺŁåıĭ
    0.33
    å®ŀæĪĺ
    0.33
    Activations Density 0.045%

    No Known Activations