© 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. 9169
    Prev
    Next
    INDEX
    Explanations

    physiological

    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
    fighter
    -0.24
    Lo
    -0.24
    令
    -0.24
    åĩĩ
    -0.24
    æĭĻ
    -0.24
    å¸Ĥéķ¿
    -0.23
    ReturnValue
    -0.23
    romise
    -0.23
     Sigma
    -0.22
    #{
    -0.22
    POSITIVE LOGITS
    æĥ³èµ·æĿ¥
    0.29
    ä¸Ģå®ļçļĦ
    0.27
    ities
    0.25
     waking
    0.25
    dzi
    0.24
    mars
    0.24
    ively
    0.24
    istically
    0.24
    ally
    0.23
    æĥ³æī¾
    0.23
    Activations Density 0.967%

    No Known Activations