© 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. 58049
    Prev
    Next
    INDEX
    Explanations

    unusual or broken text

    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
    ä¼ŀ
    -0.27
    æ¢Ń
    -0.27
    .methods
    -0.24
     rains
    -0.24
    ëĭ¹
    -0.24
    çĺ«
    -0.23
    ä½ĵç³»
    -0.23
    第ä¸Ģå±Ĭ
    -0.23
    ç²¾éĢļ
    -0.23
    çĮĽ
    -0.23
    POSITIVE LOGITS
    èIJĮ
    0.29
     ourselves
    0.29
     chalk
    0.28
    vasion
    0.27
     disposable
    0.26
    mic
    0.26
    çĸij
    0.26
    atre
    0.25
     Disposable
    0.25
     vivo
    0.25
    Activations Density 0.002%

    No Known Activations