© 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. 8402
    Prev
    Next
    INDEX
    Explanations

    blood

    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
    tor
    -0.28
    饥
    -0.26
    æĥ©ç½ļ
    -0.26
    ruk
    -0.26
    aters
    -0.25
    æĴķ
    -0.25
    imos
    -0.24
     mour
    -0.24
    èµı
    -0.24
    çIJ¬
    -0.24
    POSITIVE LOGITS
    æ£Ģæµĭ
    0.73
     labs
    0.68
     tests
    0.68
    å®ŀéªĮ室
    0.67
     laboratory
    0.66
    æµĭè¯ķ
    0.66
     lab
    0.63
     testing
    0.63
     laboratories
    0.63
    Tests
    0.56
    Activations Density 0.058%

    No Known Activations