© 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. 56416
    Prev
    Next
    INDEX
    Explanations

    technical/specialized text

    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
    æĸ¹æ¡Ī
    -0.26
    çĶ·çĶŁ
    -0.25
     mũi
    -0.25
     garbage
    -0.25
     useHistory
    -0.24
    è§Ĵ度çľĭ
    -0.24
    eve
    -0.24
    ig
    -0.24
    alus
    -0.24
    ended
    -0.24
    POSITIVE LOGITS
    mma
    0.28
    /effects
    0.28
    ntag
    0.27
    åıµ
    0.26
    为äºĨ让
    0.26
    çªģå¦Ĥåħ¶æĿ¥
    0.26
    ToAdd
    0.26
     allot
    0.25
    åħ¨åªĴä½ĵ
    0.25
    ä¼ļåıijçĶŁ
    0.25
    Activations Density 0.022%

    No Known Activations