© 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. 2039
    Prev
    Next
    INDEX
    Explanations

    bullets, shots, projectiles, ammunition

    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
     Dimensions
    -0.24
    认åIJĮ
    -0.24
     Cult
    -0.24
     newName
    -0.23
     Entr
    -0.22
    åĵºä¹³
    -0.22
    æIJŃ建
    -0.22
     hobbies
    -0.22
     newInstance
    -0.22
    _builder
    -0.21
    POSITIVE LOGITS
    åŃIJå¼¹
    0.40
     bullets
    0.39
    ä¸Ģæŀļ
    0.37
    æŀª
    0.37
     fired
    0.35
    åıijå°Ħ
    0.35
     ammunition
    0.35
     deton
    0.34
    çĤ®
    0.33
    shots
    0.32
    Activations Density 0.019%

    No Known Activations