© 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. 8411
    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
    ä¸Ī
    -0.28
    æĢ»éĥ¨
    -0.28
    Encoded
    -0.27
    -encoded
    -0.26
    anded
    -0.26
    erness
    -0.25
    éŨ
    -0.25
    èĤ¡ä»·
    -0.25
    å¿Ļ
    -0.25
    RX
    -0.24
    POSITIVE LOGITS
     himself
    0.26
     contribution
    0.25
    èĭ»
    0.25
    =head
    0.25
    CLU
    0.24
    è´¡çĮ®
    0.24
    sein
    0.24
     job
    0.24
    å°±ä¸ļ
    0.24
     employment
    0.23
    Activations Density 0.001%

    No Known Activations