© 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. 19-TRANSCODER-HP
    7. 7831
    Prev
    Next
    INDEX
    Explanations

    you

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_19.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.19.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    med
    -0.27
    abant
    -0.26
    è¿Ļä¹Ī大
    -0.25
    eenth
    -0.25
    lef
    -0.24
     PH
    -0.24
    ouro
    -0.24
    æ¥ŃåĭĻ
    -0.24
    éĹ²ç½®
    -0.24
    çı¥
    -0.24
    POSITIVE LOGITS
     observe
    0.28
    åĩºåİĤ
    0.26
    hill
    0.26
    åĩºåľº
    0.26
    èĢĮä¸į
    0.25
     дем
    0.25
    nze
    0.24
    ethoven
    0.24
    ActionTypes
    0.24
    FML
    0.23
    Activations Density 0.062%

    No Known Activations