© 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. 41324
    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
    ointment
    -0.31
    ointments
    -0.29
    èŀ¯
    -0.27
    èłķ
    -0.26
     lig
    -0.25
    æīįèĥ½
    -0.25
    aky
    -0.24
     ARISING
    -0.24
    /pi
    -0.24
    严å¯Ĩ
    -0.24
    POSITIVE LOGITS
    live
    0.30
    hei
    0.28
    mage
    0.25
    å±ŀå®ŀ
    0.25
     matte
    0.24
     apprentice
    0.24
    Atl
    0.23
    Correction
    0.23
     inconsistency
    0.23
    åĻ©
    0.23
    Activations Density 0.210%

    No Known Activations

    This feature has no known activations.