© 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. 773
    Prev
    Next
    INDEX
    Explanations

    saving or finding someone

    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
     overlays
    -0.28
    åłĨæĶ¾
    -0.27
    ç»ĻäºĪäºĨ
    -0.25
    æĸŁ
    -0.25
    å¹³æŶ
    -0.24
    éĢıéľ²
    -0.24
    æİĴéĺŁ
    -0.24
    ä¸įåIJĮç¨ĭ度
    -0.23
    äºĨä¸ĢäºĽ
    -0.23
    èµĽåĮº
    -0.23
    POSITIVE LOGITS
    æĮ½åĽŀ
    0.40
    æĭ¯æķij
    0.34
    æĮ½æķij
    0.32
     revenge
    0.31
     urgently
    0.31
    èĩªæķij
    0.30
     life
    0.30
     imm
    0.28
    æĹ©æĹ¥
    0.28
     reunited
    0.27
    Activations Density 0.049%

    No Known Activations