© 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. 40581
    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
     compromise
    -0.28
    ıntı
    -0.26
    escal
    -0.26
    ä¹ĭä½Ļ
    -0.26
     mirror
    -0.25
    mirror
    -0.25
     concepts
    -0.24
    年产
    -0.24
     very
    -0.24
     following
    -0.23
    POSITIVE LOGITS
    æĿľåħ°
    0.33
    arella
    0.31
    \Unit
    0.30
    oen
    0.29
    innie
    0.27
    溺
    0.27
    ä¸įå¿į
    0.26
    ulet
    0.26
    ä¸į便
    0.26
    reu
    0.26
    Activations Density 4.975%

    No Known Activations

    This feature has no known activations.