© 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. 22-TRANSCODER-HP
    7. 88630
    Prev
    Next
    INDEX
    Explanations

    prepositions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_22.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.22.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     anywhere
    -0.26
    á»ķ
    -0.25
    anco
    -0.24
    室å¤ĸ
    -0.23
    "For
    -0.23
     separate
    -0.22
    ách
    -0.22
     immediate
    -0.22
    鹿
    -0.22
     restricted
    -0.22
    POSITIVE LOGITS
    eday
    0.28
    preh
    0.27
    ä¹ĭæĺŁ
    0.25
    é¢Ļ
    0.25
     ObjectType
    0.25
    BarButton
    0.25
    _LONG
    0.24
    eva
    0.24
    -ln
    0.24
     Barber
    0.24
    Activations Density 0.006%

    No Known Activations