© 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. 56773
    Prev
    Next
    INDEX
    Explanations

    Product

    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
     suất
    -0.30
    çİĩ
    -0.29
    éķĢ
    -0.27
    he
    -0.26
    æĪIJ
    -0.26
    <byte
    -0.25
    夹
    -0.25
    á»ĩ
    -0.25
    æ¤ħ
    -0.24
     bikes
    -0.24
    POSITIVE LOGITS
    iac
    0.30
    åįĹè·¯
    0.27
     availability
    0.27
     information
    0.26
    elfare
    0.26
    (nil
    0.26
    anny
    0.25
    avor
    0.25
    èµĦ讯
    0.24
    astic
    0.24
    Activations Density 0.017%

    No Known Activations