© 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. 31-TRANSCODER-HP
    7. 19023
    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_31.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.31.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    æĽ´
    -0.28
    åıĺå¾ĹæĽ´åĬł
    -0.27
    æĽ´åĬł
    -0.26
    \Eloquent
    -0.24
    åıĺå¾ĹæĽ´
    -0.24
    Prov
    -0.24
    Scoped
    -0.23
    çĸı
    -0.23
    褶
    -0.23
     tablesp
    -0.23
    POSITIVE LOGITS
     greatest
    0.35
     true
    0.32
     once
    0.32
     support
    0.28
     Once
    0.27
     highest
    0.26
     closest
    0.26
     strongest
    0.25
     unst
    0.25
    ople
    0.25
    Activations Density 2.744%

    No Known Activations