© 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. 42228
    Prev
    Next
    INDEX
    Explanations

    benefit

    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
    å¤Ħæĸ¹
    -0.26
     used
    -0.25
    åı¯æĢķçļĦ
    -0.25
    èĴĭä»ĭçŁ³
    -0.25
    ä¸ĢæŃ¥ä¸ĢæŃ¥
    -0.25
    -version
    -0.24
    -plane
    -0.24
    user
    -0.23
     anthem
    -0.23
    çĶŁæ¶¯
    -0.23
    POSITIVE LOGITS
     to
    0.35
    ically
    0.32
     parents
    0.30
     homes
    0.29
     providers
    0.29
     employers
    0.29
     governments
    0.28
     environments
    0.28
     businesses
    0.28
     institutions
    0.28
    Activations Density 0.002%

    No Known Activations