© 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. 2536
    Prev
    Next
    INDEX
    Explanations

    police, authorities, alarm, contact

    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
    mant
    -0.28
    ipse
    -0.23
    çģµæ´»
    -0.23
    æĻĴ
    -0.23
    æ¯ıå¹´
    -0.23
    骨
    -0.22
    anken
    -0.22
    cmb
    -0.22
     ATH
    -0.22
    ç¾½
    -0.22
    POSITIVE LOGITS
     police
    0.33
    æĬ¥èѦ
    0.32
    第ä¸ĢæŶéĹ´
    0.32
     promptly
    0.28
     alerted
    0.28
    æ±ĤåĬ©
    0.27
     alarm
    0.26
    Police
    0.26
     authorities
    0.26
     immediately
    0.26
    Activations Density 0.038%

    No Known Activations