© 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. 9022
    Prev
    Next
    INDEX
    Explanations

    control

    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
    lier
    -0.32
     Prize
    -0.27
     lia
    -0.24
    between
    -0.24
    ircular
    -0.24
     bur
    -0.24
    bole
    -0.23
     linker
    -0.23
    oley
    -0.23
    ugged
    -0.23
    POSITIVE LOGITS
    æݧåĪ¶
    0.91
     controlling
    0.84
     control
    0.79
     controls
    0.71
     controlled
    0.71
     Control
    0.70
     æݧ
    0.70
    control
    0.68
    Control
    0.66
    -control
    0.64
    Activations Density 0.001%

    No Known Activations