© 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. 8255
    Prev
    Next
    INDEX
    Explanations

    it

    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
    æ¼ł
    -0.25
    èļĬ
    -0.25
    ä¸įåħĭ
    -0.24
     posix
    -0.23
    opic
    -0.23
    _least
    -0.23
    eler
    -0.23
    uite
    -0.23
    æ¯Ķå¦Ĥ说
    -0.23
     profess
    -0.23
    POSITIVE LOGITS
     ARM
    0.28
    çijķ
    0.26
    plemented
    0.25
    ismatic
    0.25
     waited
    0.25
    tam
    0.25
     Omn
    0.24
    ifies
    0.24
     ages
    0.24
     climates
    0.24
    Activations Density 0.162%

    No Known Activations