© 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. 41215
    Prev
    Next
    INDEX
    Explanations

    health care

    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
    头ä¸Ĭ
    -0.31
    ầu
    -0.27
    clusive
    -0.27
    æµĶ
    -0.26
    uem
    -0.25
    æľ¬åľ°
    -0.25
    é¹ij
    -0.25
    ZE
    -0.25
    Thumb
    -0.25
    å¢ī
    -0.24
    POSITIVE LOGITS
     volume
    0.31
     Volume
    0.29
     Growth
    0.28
    ndef
    0.27
    æĪĺçķ¥
    0.27
     growth
    0.27
     ton
    0.25
    æĶ¹åĪ¶
    0.25
    opus
    0.25
    åĪĽ
    0.25
    Activations Density 0.009%

    No Known Activations