© 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. 40820
    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
    ĴĮ
    -0.32
     slim
    -0.29
     mũi
    -0.28
    æĢ»åħ¬åı¸
    -0.26
    uien
    -0.26
    解éĩĬ
    -0.26
    pert
    -0.25
     OnTriggerEnter
    -0.24
    inet
    -0.24
     Charm
    -0.24
    POSITIVE LOGITS
    /trunk
    0.27
    gba
    0.26
    .nz
    0.26
    edd
    0.25
    ching
    0.25
    ãĤį
    0.24
    帧
    0.24
    ÑĢаÐ
    0.24
    nez
    0.24
    edb
    0.24
    Activations Density 0.064%

    No Known Activations

    This feature has no known activations.