© 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. 7982
    Prev
    Next
    INDEX
    Explanations

    comma

    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
     TICK
    -0.31
    ä½ı
    -0.27
    enko
    -0.27
    åij½
    -0.25
     particular
    -0.25
     comforting
    -0.25
     tol
    -0.24
    åij·
    -0.24
    .net
    -0.24
    å¿į
    -0.24
    POSITIVE LOGITS
    è¯ķ
    0.31
    ä¿®
    0.28
    emie
    0.26
    ãĥĬãĥ¼
    0.26
     Concurrent
    0.25
    illum
    0.25
    :last
    0.25
    iming
    0.25
     interle
    0.25
    bish
    0.24
    Activations Density 0.014%

    No Known Activations