© 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. 14-TRANSCODER-HP
    7. 40372
    Prev
    Next
    INDEX
    Explanations

    Associations, tasks, events

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_14.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.14.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    åķģ
    -0.31
     breached
    -0.29
    пон
    -0.28
    ,NULL
    -0.27
     EVT
    -0.27
    è¾ĵç»Ļ
    -0.25
    pisa
    -0.24
    æŃ»èĢħ
    -0.24
     LIVE
    -0.24
    çĦļ
    -0.24
    POSITIVE LOGITS
    aries
    0.28
    ç¸
    0.27
     trap
    0.27
    ers
    0.26
    æŀ
    0.26
    æľºä¼ļ
    0.25
    çĴ
    0.25
     Gamb
    0.25
    swick
    0.25
    izzes
    0.25
    Activations Density 0.167%

    No Known Activations