© 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. 7262
    Prev
    Next
    INDEX
    Explanations

    about

    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
    eus
    -0.28
    tok
    -0.28
    intent
    -0.28
    abb
    -0.26
    å¾Īé«ĺçļĦ
    -0.25
    ange
    -0.24
    inst
    -0.24
    _tok
    -0.24
     volte
    -0.24
    avan
    -0.23
    POSITIVE LOGITS
    æĹłå¥Ī
    0.30
    rians
    0.28
    ç±³å°Ķ
    0.27
    鸢
    0.27
    ndata
    0.26
    æĺ¯çľŁçļĦ
    0.26
    roups
    0.25
    adt
    0.24
    å¡ĺ
    0.24
    åĩıéĢŁ
    0.24
    Activations Density 0.012%

    No Known Activations