© 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. 9085
    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
    ,application
    -0.31
     application
    -0.29
     inclusion
    -0.28
    Expired
    -0.27
    åºĶçĶ¨
    -0.26
    çĬ¶æĢģ
    -0.26
     aplicación
    -0.25
    çļĦåºĶçĶ¨
    -0.25
    unique
    -0.25
    jem
    -0.25
    POSITIVE LOGITS
    ãĥªãĤ¢
    0.28
    usher
    0.27
     fid
    0.26
    .Person
    0.25
    çķ
    0.25
     Attached
    0.25
    对åħ¬åı¸
    0.25
    æ´ģçĻ½
    0.24
     PERSON
    0.24
    对人ä½ĵ
    0.24
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.