© 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. 57134
    Prev
    Next
    INDEX
    Explanations

    possessive pronouns

    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
    Not in Any Lists

    No Comments

    Negative Logits
    emean
    -0.31
    å¹²æ¶ī
    -0.28
    åįıå®ļ
    -0.27
     Apps
    -0.27
    -valu
    -0.26
    é¢
    -0.26
     Wyatt
    -0.26
    pack
    -0.25
    ighted
    -0.25
    Value
    -0.25
    POSITIVE LOGITS
     minority
    0.29
    cq
    0.27
     bè
    0.25
     zo
    0.25
     struggle
    0.25
    è°Ĺ
    0.25
    ethereum
    0.24
    åij¨ãĤĬ
    0.24
    讽
    0.24
    ablish
    0.23
    Activations Density 1.700%

    No Known Activations