© 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. 39881
    Prev
    Next
    INDEX
    Explanations

    Networking and code

    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
     Mal
    -0.27
    èĦ¯
    -0.26
    ATALOG
    -0.26
    满æĦı度
    -0.26
    URE
    -0.26
    nds
    -0.26
     mast
    -0.26
    æ¿Ĵ
    -0.25
    inator
    -0.25
    è°Ķ
    -0.25
    POSITIVE LOGITS
    大家åĪĨ享
    0.30
    аниÑĨ
    0.30
    æIJŃ
    0.28
    è¶ĬæĿ¥
    0.26
    icism
    0.26
    çļĦè¯Ŀ
    0.25
    _kw
    0.25
    "+"
    0.25
    vents
    0.25
    ffc
    0.25
    Activations Density 0.150%

    No Known Activations