© 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. 8515
    Prev
    Next
    INDEX
    Explanations

    code/names

    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
    odem
    -0.28
    aning
    -0.28
    Propagation
    -0.26
    ä»»ä½ķ人éĥ½
    -0.26
    èIJ¥åħ»ä»·åĢ¼
    -0.26
    gh
    -0.25
    Rare
    -0.25
    Hits
    -0.25
     Hits
    -0.25
    erca
    -0.24
    POSITIVE LOGITS
    çģ«çĥ§
    0.26
    ijkl
    0.25
    ardless
    0.24
    erton
    0.24
     charter
    0.24
    utos
    0.24
    etto
    0.23
     Kurdistan
    0.23
    ¢åįķ
    0.23
     stood
    0.23
    Activations Density 0.000%

    No Known Activations