© 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. 27-TRANSCODER-HP
    7. 8820
    Prev
    Next
    INDEX
    Explanations

    accord

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_27.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.27.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     corpor
    -0.28
    elocity
    -0.27
    ÑĤÑĢ
    -0.25
    -pin
    -0.24
     twin
    -0.23
     unc
    -0.23
     Pin
    -0.23
    hattan
    -0.23
     pin
    -0.23
    éļĽ
    -0.23
    POSITIVE LOGITS
    å¼¹
    0.29
    åIJĮä¸Ģ
    0.25
    razil
    0.25
    ments
    0.25
    ascar
    0.25
    tti
    0.25
    æĶ¹éĿ©åĪĽæĸ°
    0.24
    å¾Ģ
    0.24
    åįľ
    0.24
    æĦŁ
    0.24
    Activations Density 0.002%

    No Known Activations