© 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. 40664
    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
    Callable
    -0.27
    uk
    -0.25
    ">#
    -0.25
    æĶ¯ä»ĺ
    -0.24
    罪
    -0.24
     CDDL
    -0.24
     IonicModule
    -0.24
    大人
    -0.23
    çĭ»
    -0.23
    irs
    -0.23
    POSITIVE LOGITS
     separat
    0.26
     sho
    0.26
     tightly
    0.25
    ضة
    0.24
    tti
    0.24
    çļĦä¸ĢéĿ¢
    0.24
    optic
    0.24
    éĻ¤åİ»
    0.24
    OrNull
    0.24
     Kob
    0.24
    Activations Density 0.091%

    No Known Activations

    This feature has no known activations.