© 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. 27-TRANSCODER-HP
    7. 57208
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_27.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.27.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    inium
    -0.28
    达人
    -0.26
    å°ıé¢Ŀ
    -0.26
    unction
    -0.26
    templates
    -0.25
    éªļæī°
    -0.25
    inz
    -0.24
    è¾IJ
    -0.24
    åĽ¾çº¸
    -0.24
    ills
    -0.23
    POSITIVE LOGITS
    åºĶä»ĺ
    0.26
    CAPE
    0.26
     ram
    0.25
     –
    0.25
    宣
    0.25
    éĺ´éĺ³
    0.24
    ively
    0.24
     HOLDERS
    0.24
    纵横
    0.23
     ton
    0.23
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.