© 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. Qwen3-4B
    5. 18-TRANSCODER-HP
    7. 88653
    Prev
    Next
    INDEX
    Explanations

    flood

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_18.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.18.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ÑĢазвива
    -0.27
    麸
    -0.26
    viz
    -0.24
    ç»ıæµİæįŁå¤±
    -0.24
    çĥ¦
    -0.24
    inine
    -0.23
    izabeth
    -0.23
    主義
    -0.23
     èĩªåĬ¨çĶŁæĪIJ
    -0.23
    éĶ¯
    -0.23
    POSITIVE LOGITS
     depr
    0.29
    åºĸ
    0.28
     purpos
    0.27
     scrap
    0.27
    ates
    0.26
     intention
    0.25
    æĭİ
    0.25
     scars
    0.25
     intents
    0.25
     especial
    0.25
    Activations Density 9.237%

    No Known Activations