© 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. 53306
    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
    èĪ¬
    -0.27
    final
    -0.27
    erez
    -0.27
    åĩłä½ķ
    -0.25
     final
    -0.25
    Geometry
    -0.25
    _final
    -0.25
     geometry
    -0.24
     Singh
    -0.24
    comb
    -0.24
    POSITIVE LOGITS
    /ic
    0.27
    ="#">↵
    0.26
    obbled
    0.25
    éħĿ
    0.24
    è§ħ
    0.24
    (rec
    0.23
    ç¾ģ
    0.23
    æĮijè¡ħ
    0.23
     #↵↵
    0.23
    sein
    0.23
    Activations Density 0.101%

    No Known Activations

    This feature has no known activations.