© 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. 8683
    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
     phones
    -0.31
    Phones
    -0.30
    prises
    -0.29
    arak
    -0.27
    [tmp
    -0.26
    enade
    -0.26
    æĢ§åĪ«
    -0.25
    (es
    -0.25
    ä¼Ļä¼´åħ³ç³»
    -0.25
    osity
    -0.25
    POSITIVE LOGITS
    -Smith
    0.29
     implementations
    0.29
     computations
    0.29
     hashes
    0.28
     simulation
    0.28
     algorithm
    0.27
    smith
    0.27
     software
    0.27
     GUI
    0.26
     Gujar
    0.26
    Activations Density 0.100%

    No Known Activations