© 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. 56742
    Prev
    Next
    INDEX
    Explanations

    Names and Locations

    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
    è£ĺ
    -0.29
    çļĦ羣å®ŀ
    -0.27
    b
    -0.26
     betray
    -0.25
    çħľ
    -0.25
    Z
    -0.25
    é£ŀæľº
    -0.24
    POCH
    -0.24
    çĶµæ±ł
    -0.24
    Aut
    -0.23
    POSITIVE LOGITS
    izr
    0.30
    ylvania
    0.30
     entidad
    0.28
     Unified
    0.27
    èŀĪ
    0.26
    '].$
    0.25
     Rodrig
    0.25
     repl
    0.25
    绣ä¸Ģ
    0.25
    å°ıç¼ĸä¸Ģèµ·
    0.25
    Activations Density 0.002%

    No Known Activations