© 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. 58191
    Prev
    Next
    INDEX
    Explanations

    able

    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
    aign
    -0.30
    lide
    -0.28
    ä¸ĸçķĮè§Ĥ
    -0.26
     Stranger
    -0.25
    æĸĩæĺİ
    -0.25
    å±İ
    -0.25
    .testng
    -0.25
    æĹ¶ä»£ä¸ŃåĽ½
    -0.24
    distinct
    -0.24
    enis
    -0.24
    POSITIVE LOGITS
    åijĬè¯īä»ĸ
    0.29
    åijĬè¯ī
    0.28
     tell
    0.27
     assess
    0.27
    ç»Łè®¡
    0.27
    åĪĨæŀIJå¸Ī
    0.26
    éĹ®
    0.25
     could
    0.25
     automáticamente
    0.25
     ask
    0.24
    Activations Density 0.011%

    No Known Activations