© 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. 33-TRANSCODER-HP
    7. 53127
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_33.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.33.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    å¿ĥçģµ
    -0.30
    çģµ
    -0.26
    Paths
    -0.26
    å¼ĢæĿ¥
    -0.26
    è¡Į
    -0.26
     Hed
    -0.25
    è¾Ł
    -0.25
     Science
    -0.25
     Minds
    -0.25
    ä»ĸ们æĺ¯
    -0.25
    POSITIVE LOGITS
    -translate
    0.25
    çī¹èī²çļĦ
    0.24
     stal
    0.24
    ä»¥ä¹łè¿ijå¹³
    0.24
    æĹ¥çĶµ
    0.24
     MV
    0.24
    pak
    0.24
     static
    0.24
     concealed
    0.24
    pliers
    0.23
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.