© 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. 22-TRANSCODER-HP
    7. 129697
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_22.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.22.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Read
    -0.25
    asu
    -0.25
    PIP
    -0.25
    ä¸įæĪIJ
    -0.24
    burg
    -0.24
    港åĮº
    -0.24
    åŁİå¸ĤçļĦ
    -0.24
    locking
    -0.24
    reads
    -0.23
    park
    -0.23
    POSITIVE LOGITS
    ament
    0.32
    ement
    0.31
    å¹´çĶ±
    0.28
    ama
    0.28
    æĥħåĨµè¿Ľè¡Į
    0.28
     fund
    0.25
    abela
    0.25
    SCP
    0.25
    éĶ£
    0.25
    Lic
    0.24
    Activations Density 1.878%

    No Known Activations

    This feature has no known activations.