© 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. 40869
    Prev
    Next
    INDEX
    Explanations

    Code, music, document headers

    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
    梦è§ģ
    -0.30
    è§ģ
    -0.27
     Tester
    -0.25
    æŀķ
    -0.24
    è¹Ī
    -0.24
    ersive
    -0.24
    aign
    -0.24
    меди
    -0.24
    dess
    -0.24
    yo
    -0.24
    POSITIVE LOGITS
    西路
    0.31
    åĪĨå±Ģ
    0.29
     EventArgs
    0.24
    幡
    0.24
     chill
    0.24
    åĩºè¡Į
    0.24
    èķĬ
    0.24
    讯
    0.24
    两岸
    0.24
    èĤī
    0.23
    Activations Density 0.096%

    No Known Activations