© 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. 40821
    Prev
    Next
    INDEX
    Explanations

    research articles

    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
    æĪĽ
    -0.24
    rink
    -0.24
    enci
    -0.24
    sdk
    -0.24
    æį
    -0.24
    å¸ĪäºĭåĬ¡æīĢ
    -0.24
     vriend
    -0.24
    feof
    -0.24
    ä¹¡åľŁ
    -0.24
    duration
    -0.24
    POSITIVE LOGITS
    èĩ³äºİ
    0.27
    !;↵
    0.25
     simpler
    0.24
    åºĬä¸Ĭ
    0.24
    å®īåĢį
    0.24
     hole
    0.24
    æĽ´ä¸º
    0.24
     sec
    0.23
     AppComponent
    0.23
     recreate
    0.23
    Activations Density 0.538%

    No Known Activations