© 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. 27-TRANSCODER-HP
    7. 57200
    Prev
    Next
    INDEX
    Explanations

    Snippets of articles

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_27.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.27.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    æīĵçł´äºĨ
    -0.28
    éķį
    -0.25
    ä¸Ģè§Ĵ
    -0.25
    ä¼ļ对
    -0.24
    `).
    -0.24
    ä¸Ģ人
    -0.24
    iated
    -0.23
    åĪĽéĢłäºĨ
    -0.23
    amiento
    -0.23
     Kenn
    -0.23
    POSITIVE LOGITS
     happening
    0.27
    udem
    0.26
    鸮
    0.26
    Nullable
    0.25
    亮
    0.25
    zag
    0.25
    ä¹Łå¼Ģå§ĭ
    0.25
    ifes
    0.24
    å¿«éĢŁ
    0.24
     Mostly
    0.24
    Activations Density 0.007%

    No Known Activations