© 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. 27-TRANSCODER-HP
    7. 7866
    Prev
    Next
    INDEX
    Explanations

    NamesReason: Common theme of names in TOP_ACTIVATING_TEXTS

    np_max-act-logits · gemini-2.0-flash
    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
    Negative Logits
    æݨåIJij
    -0.30
    åĽŀåĪ°
    -0.29
    ERIC
    -0.28
    adamente
    -0.28
    łģ
    -0.27
    paginate
    -0.26
    æݨ
    -0.25
    енÑĤÑĢ
    -0.25
    å¹¼ç¨ļ
    -0.24
    ured
    -0.24
    POSITIVE LOGITS
    Fatal
    0.28
    respons
    0.25
     Cam
    0.25
    XB
    0.25
     Remote
    0.24
    ละà¸Ħร
    0.24
    Unnamed
    0.24
    çİĩ为
    0.24
    çī¹åĪ«å£°æĺİ
    0.23
    Flex
    0.23
    Activations Density 0.002%

    No Known Activations