© 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. 112239
    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
    åħ¨èĥ½
    -0.27
    ì¹¼
    -0.27
    大çīĩ
    -0.25
    ocol
    -0.24
    头çļ®
    -0.24
    æµģ产
    -0.24
    åĬłéĢŁ
    -0.23
    éĴ±
    -0.23
    棱
    -0.23
    LESS
    -0.23
    POSITIVE LOGITS
     [âĢ¦
    0.25
    æ¹ľ
    0.25
     Sit
    0.24
    atra
    0.24
    Ops
    0.24
    âĢ¦I
    0.24
    âĢ¦it
    0.23
    æ¼³
    0.23
    çľ¼åīįçļĦ
    0.23
     »,
    0.23
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.