© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 25-TRANSCODER-HP
    7. 109586
    Prev
    Next
    INDEX
    Explanations

    like/likes

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_25.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.25.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    sand
    -0.31
    quer
    -0.31
    TypeEnum
    -0.30
    shm
    -0.28
    kest
    -0.28
    第ä¸Ģéĥ¨
    -0.27
    ä¸Ģç±»
    -0.25
    obel
    -0.25
    iciel
    -0.25
    åĥı
    -0.23
    POSITIVE LOGITS
    HT
    0.26
     HT
    0.26
    çļĦçIJĨçĶ±
    0.25
    _ht
    0.24
     led
    0.24
    çIJĨçĶ±
    0.23
    æıIJä¾ĽæĽ´å¤ļ
    0.23
     Led
    0.23
    建
    0.23
    缸æ¯Ķäºİ
    0.23
    Activations Density 0.114%

    No Known Activations