© 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. 7216
    Prev
    Next
    INDEX
    Explanations

    to, in

    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
     pet
    -0.29
    è¨ĢãģĨ
    -0.26
     sober
    -0.25
    SED
    -0.25
     specificity
    -0.25
    ubits
    -0.24
    prene
    -0.24
     CFR
    -0.24
    .pet
    -0.24
     ceased
    -0.23
    POSITIVE LOGITS
    osit
    0.28
    åį°
    0.27
    organic
    0.26
    (Label
    0.25
    ground
    0.25
    èĻı
    0.24
    irma
    0.24
    ä¸įå°ij人
    0.24
    Unnamed
    0.24
    cts
    0.24
    Activations Density 0.013%

    No Known Activations