© 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. 32-TRANSCODER-HP
    7. 41865
    Prev
    Next
    INDEX
    Explanations

    trauma

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_32.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.32.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    sembly
    -0.26
    带
    -0.26
    带ä¸Ĭ
    -0.25
    设计æĸ¹æ¡Ī
    -0.25
     cref
    -0.24
    åŁºæķ°
    -0.24
    GetMethod
    -0.24
    oundary
    -0.23
    _TypeDef
    -0.23
    HEME
    -0.23
    POSITIVE LOGITS
     impacting
    0.33
     resulted
    0.32
     affecting
    0.31
     acquired
    0.30
    éĻĨ
    0.28
    è·¤
    0.27
     while
    0.27
    _while
    0.27
     incurred
    0.27
     resulting
    0.26
    Activations Density 0.003%

    No Known Activations