© 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. 88021
    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
    ymm
    -0.23
    cae
    -0.22
    assist
    -0.22
     Um
    -0.22
    iders
    -0.21
    纡
    -0.21
    çºĤ
    -0.21
    .reverse
    -0.21
    ixon
    -0.21
    æĢĿãģĨ
    -0.21
    POSITIVE LOGITS
    ä¸įèĪį
    0.25
     tort
    0.25
    oret
    0.23
     namedtuple
    0.23
     camb
    0.23
     flesh
    0.23
    çļĦæĥħå½¢
    0.22
    ä¾ĽåºĶ
    0.22
     TORT
    0.22
    ä¸įå¿į
    0.22
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.