© 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. 40081
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
     lenses
    -0.26
    æĥħåĨµè¿Ľè¡Į
    -0.26
    çļĦ人æĿ¥è¯´
    -0.26
    çļĦ缮åħī
    -0.26
    ursions
    -0.25
    å¾®è§Ĥ
    -0.25
    /trunk
    -0.25
    lections
    -0.24
    CharCode
    -0.24
    _calls
    -0.24
    POSITIVE LOGITS
    dio
    0.27
     üst
    0.26
    çĸ¾çĹħ
    0.26
    arium
    0.24
    åĬŁè¯¾
    0.24
    icz
    0.24
    bell
    0.24
    ç½Ĺ
    0.23
     Exhibition
    0.23
    ÅĻ
    0.23
    Activations Density 0.004%

    No Known Activations

    This feature has no known activations.