© 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. 41043
    Prev
    Next
    INDEX
    Explanations

    Common words in mixed languages

    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
    ffective
    -0.29
    æīĢ说
    -0.27
    æľķ
    -0.26
     clr
    -0.25
    rub
    -0.25
     realizing
    -0.25
     Effective
    -0.25
    áĥ¬
    -0.25
    æĬĬè¿ĻäºĽ
    -0.25
     translating
    -0.25
    POSITIVE LOGITS
    ä¼
    0.29
    壹
    0.27
     {\↵
    0.26
    BootApplication
    0.26
    å®īåħ¨æĢ§
    0.26
    æĤ²è§Ĥ
    0.26
    çĶŁæŃ»
    0.26
    boats
    0.25
    atology
    0.25
     comparatively
    0.25
    Activations Density 0.753%

    No Known Activations