© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 9-TRANSCODER-HP
    7. 29460
    Prev
    Next
    INDEX
    Explanations

    microbi

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_9.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.9.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     KeyboardInterrupt
    -0.26
    çľĭå®Į
    -0.25
    é¾Ĭ
    -0.24
    çľĭè¿ĩ
    -0.24
     Dag
    -0.24
     creditor
    -0.23
    åĢĴéĹŃ
    -0.23
    utzer
    -0.23
    è¯Ħ审
    -0.23
    åĩŃä»Ģä¹Ī
    -0.23
    POSITIVE LOGITS
    tell
    0.26
    websocket
    0.26
    vas
    0.26
    约æĿŁ
    0.24
    joint
    0.24
    å½¢å¼ı
    0.24
    outputs
    0.24
     Seasons
    0.24
    bon
    0.24
    OMPI
    0.24
    Activations Density 5.242%

    No Known Activations