© 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. 8334
    Prev
    Next
    INDEX
    Explanations

    highly valued things

    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
    æľīæĦıä¹ī
    -0.30
    į°
    -0.30
    è§Ħå¾ĭ
    -0.29
     evidence
    -0.28
    änder
    -0.26
    头åıij
    -0.26
    ongan
    -0.25
    è¯ģæį®
    -0.25
    æ¯Ķéĩį
    -0.25
    atively
    -0.24
    POSITIVE LOGITS
     stalk
    0.28
    statt
    0.28
     Xm
    0.26
     Bond
    0.25
    scribe
    0.24
    è¯ļ
    0.24
    å±ı
    0.24
    ä¾Ľå¤§å®¶
    0.23
    thest
    0.23
    /error
    0.23
    Activations Density 0.219%

    No Known Activations