© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 19-TRANSCODER-HP
    7. 7242
    Prev
    Next
    INDEX
    Explanations

    Personal opinions and statements

    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
    procedure
    -0.27
    pragma
    -0.25
    wares
    -0.25
    erset
    -0.24
    frag
    -0.24
    ounces
    -0.24
     Zah
    -0.24
    oted
    -0.23
     Procedure
    -0.23
    etter
    -0.23
    POSITIVE LOGITS
    icia
    0.30
    交代
    0.29
    ãģĦãģŁãĤī
    0.28
    éĿ¢
    0.26
     intervene
    0.26
    ä¸Ńåħ³
    0.26
    éĢģ
    0.26
    iola
    0.25
    .Roll
    0.24
    VAS
    0.24
    Activations Density 0.031%

    No Known Activations