© 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. 8836
    Prev
    Next
    INDEX
    Explanations

    say ending with -mediate

    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
     setuptools
    -0.32
    erus
    -0.30
    åĨħéĥ¨æݧåĪ¶
    -0.28
    å¦Ĥæľīä¾µæĿĥ
    -0.27
    bul
    -0.26
    .extensions
    -0.26
     Hind
    -0.26
    æľ¬æĬ¥
    -0.26
    ilot
    -0.25
    ä¼ļéķ¿
    -0.25
    POSITIVE LOGITS
    atory
    0.26
    apping
    0.25
     restored
    0.25
    Together
    0.25
    说äºĨ
    0.25
    aga
    0.25
     together
    0.25
    uality
    0.24
    INATION
    0.24
    èĭĹ
    0.24
    Activations Density 0.003%

    No Known Activations