© 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. 57967
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    åıĸ
    -0.27
     interference
    -0.27
     Maul
    -0.27
    ê°ij
    -0.27
    пÑĢÑı
    -0.26
    efe
    -0.26
    rone
    -0.25
    INNER
    -0.24
    à¹Ĥà¸Ļ
    -0.24
     %@
    -0.23
    POSITIVE LOGITS
    ç»Ħç»ĩå¼Ģå±ķ
    0.28
     неÑģк
    0.27
     chast
    0.26
    /cpp
    0.26
    arios
    0.26
    commercial
    0.25
    acter
    0.25
    ogs
    0.25
     arrang
    0.24
     arts
    0.24
    Activations Density 0.002%

    No Known Activations

    This feature has no known activations.