© 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. 8789
    Prev
    Next
    INDEX
    Explanations

    of

    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
    .deep
    -0.28
    PLIED
    -0.25
    ãģ¨ãģĦãģ£ãģŁ
    -0.25
    variant
    -0.25
    :</
    -0.24
    éĺ®
    -0.24
    å°¾
    -0.24
    success
    -0.23
    æŁ¥çľĭ详æĥħ
    -0.23
    çīĪ
    -0.23
    POSITIVE LOGITS
    ä¸ľè¥¿
    0.28
     surv
    0.26
    ibase
    0.26
    ä¾¦å¯Ł
    0.26
    论
    0.25
    çı
    0.25
    ssf
    0.25
    èģĭ
    0.23
    ç¬Ķ
    0.23
    Animated
    0.23
    Activations Density 0.060%

    No Known Activations