© 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. 88049
    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
    人寿
    -0.26
    个çĻ¾åĪĨçĤ¹
    -0.24
    BackPressed
    -0.23
    èĩªè¡Į车
    -0.23
    lichkeit
    -0.23
    çijĻ
    -0.23
    manual
    -0.23
    çĶ¨éĩı
    -0.23
    éªijè¡Į
    -0.23
    =\"%
    -0.23
    POSITIVE LOGITS
     wouldn
    0.24
     Gors
    0.24
    .combine
    0.24
     Machine
    0.24
    cur
    0.24
    izard
    0.23
    alles
    0.23
    Cur
    0.23
     curvature
    0.23
    earch
    0.22
    Activations Density 0.071%

    No Known Activations

    This feature has no known activations.