© 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. 7535
    Prev
    Next
    INDEX
    Explanations

    I

    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
    åµĺ
    -0.27
    ĪæĿĥ
    -0.26
     poems
    -0.26
    atoria
    -0.25
     poem
    -0.25
    endon
    -0.24
    (fe
    -0.24
    ãĥ¼ãĤ¿ãĥ¼
    -0.24
    acyj
    -0.24
    yles
    -0.23
    POSITIVE LOGITS
    edin
    0.26
     Åļw
    0.25
    èĤ¯å®ļ
    0.25
    tas
    0.25
    &action
    0.23
    æľīçļĦ
    0.23
    çĶ¨æ°´
    0.23
    &C
    0.23
     Madden
    0.23
     thanked
    0.23
    Activations Density 0.096%

    No Known Activations