© 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. 22-TRANSCODER-HP
    7. 98303
    Prev
    Next
    INDEX
    Explanations

    Possessive pronouns

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_22.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.22.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¸Ńå°ıåŀĭ
    -0.29
    éĻĮ
    -0.26
    AH
    -0.26
    antal
    -0.25
     tá»Ń
    -0.25
    geh
    -0.25
    adratic
    -0.24
    æīĢéľĢè¦ģçļĦ
    -0.24
    opl
    -0.24
    azed
    -0.24
    POSITIVE LOGITS
     bearing
    0.29
    afone
    0.28
    lete
    0.26
    .Rem
    0.26
    åİ»è¿ĩ
    0.26
    INLINE
    0.25
     policy
    0.25
    null
    0.25
    policy
    0.25
     inline
    0.25
    Activations Density 0.027%

    No Known Activations