© 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. 88030
    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
    eden
    -0.31
    第äºĮ次
    -0.27
    æģ°
    -0.27
    лиÑģÑĤ
    -0.26
     triple
    -0.25
    åĬĽåѦ
    -0.24
    á»Ļ
    -0.24
    nullable
    -0.24
    reds
    -0.24
    alcon
    -0.23
    POSITIVE LOGITS
    æ²¥
    0.29
    łéĻ¤
    0.27
    gorithm
    0.26
    åĵĵ
    0.26
     Congressional
    0.26
    .xlim
    0.26
    çĪ·
    0.25
    å¹´åĨħ
    0.25
    .ylim
    0.24
    ivo
    0.24
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.