© 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. 7180
    Prev
    Next
    INDEX
    Explanations

    space

    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
    ç²ī
    -0.28
     Explosion
    -0.25
    gest
    -0.25
    rede
    -0.24
    ä»ĺ
    -0.24
     anywhere
    -0.24
     gest
    -0.23
    .microsoft
    -0.23
     wrists
    -0.22
    swing
    -0.22
    POSITIVE LOGITS
    ä¸īæľŁ
    0.31
    ãĤ«ãĥ¼
    0.28
    严åİīæīĵåĩ»
    0.27
    igos
    0.27
    empl
    0.27
    åıªæľīä¸Ģ个
    0.27
    ä¸įä¿¡
    0.26
    egin
    0.25
    ev
    0.25
    éªĦ
    0.25
    Activations Density 0.702%

    No Known Activations