© 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. 40220
    Prev
    Next
    INDEX
    Explanations

    Unstructured and mixed content

    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
    inci
    -0.29
    aux
    -0.28
     )]↵
    -0.27
    ()))č↵
    -0.26
     ]]↵
    -0.26
    latable
    -0.26
    éģĹçķĻ
    -0.26
     aux
    -0.25
     Nab
    -0.25
     Aux
    -0.25
    POSITIVE LOGITS
     yyn
    0.27
    åIJĮä¸ļ
    0.25
    æĪij说
    0.25
    è¿ĩçļĦ
    0.25
    xec
    0.25
    enever
    0.25
    yps
    0.25
     má»įi
    0.24
    çĦ¶
    0.24
    ä¸ĩ个
    0.24
    Activations Density 0.225%

    No Known Activations