© 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. 25-TRANSCODER-HP
    7. 108090
    Prev
    Next
    INDEX
    Explanations

    technical mixed content

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_25.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.25.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     sent
    -0.29
    ä¸Ģç¬Ķ
    -0.28
    na
    -0.27
    sent
    -0.27
    åĽŀ
    -0.27
    åĩº
    -0.26
    isson
    -0.26
    ä¸Ģè½®
    -0.25
    DROP
    -0.25
    nis
    -0.25
    POSITIVE LOGITS
     strugg
    0.26
    æĮ¨
    0.25
    arter
    0.25
    FromArray
    0.25
    _addresses
    0.25
    offee
    0.24
     pollut
    0.24
     dise
    0.24
     incent
    0.24
     davran
    0.23
    Activations Density 0.126%

    No Known Activations