© 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. 14-TRANSCODER-HP
    7. 40998
    Prev
    Next
    INDEX
    Explanations

    Topic

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_14.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.14.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    antly
    -0.30
    PointerException
    -0.27
    anz
    -0.27
    wise
    -0.26
     added
    -0.26
    atus
    -0.25
     COM
    -0.25
     IDD
    -0.24
    å¾ĹåĪĨ
    -0.24
    Fixture
    -0.24
    POSITIVE LOGITS
    ä¹Łæĺ¯éĿŀ常
    0.31
    ä½łçİ°åľ¨
    0.27
    laÅŁ
    0.27
    vc
    0.27
    ÙĩÙĬ
    0.27
    din
    0.25
     Mim
    0.25
     vc
    0.24
     suspend
    0.24
    æŦ
    0.23
    Activations Density 1.009%

    No Known Activations