© 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. 40908
    Prev
    Next
    INDEX
    Explanations

    Massive

    np_max-act · gemini-2.0-flash
    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
    丧
    -0.28
     Gri
    -0.25
    çIJĨæĥ³ä¿¡å¿µ
    -0.25
    apiro
    -0.24
    åıĮåIJij
    -0.24
    éĢIJå¹´
    -0.24
    èĩĬ
    -0.24
    lear
    -0.24
    åĬŀäºĭ
    -0.23
     learning
    -0.23
    POSITIVE LOGITS
    etics
    0.29
    éħįèµĦ
    0.27
    mits
    0.27
    mere
    0.26
    chin
    0.25
    xfb
    0.25
    utos
    0.25
     zob
    0.25
    �t
    0.24
    çľīæ¯Ľ
    0.24
    Activations Density 0.659%

    No Known Activations