© 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. 8933
    Prev
    Next
    INDEX
    Explanations

    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
    å¦Ĥä½ķ
    -0.34
    å¦Ĥä½ķåİ»
    -0.32
     cómo
    -0.28
     ways
    -0.28
    è·Łå¥¹
    -0.28
    è·Łä»ĸ
    -0.27
    æĺ¯æĢİæł·
    -0.26
    æĺ¯æĢİä¹Ī
    -0.26
    æĺ¯å¦Ĥä½ķ
    -0.26
    åľ¨æĪij
    -0.26
    POSITIVE LOGITS
     they
    0.50
     it
    0.40
    they
    0.36
     that
    0.35
     we
    0.35
    å®ĥ
    0.31
    ä»ĸ们
    0.30
     они
    0.28
     she
    0.28
     you
    0.28
    Activations Density 0.036%

    No Known Activations