© 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. 9-TRANSCODER-HP
    7. 29608
    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_9.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.9.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°Ĭæķ¬
    -0.28
    èĢĮæĪIJ
    -0.26
    vere
    -0.26
    ç²¾éĢļ
    -0.26
    perfect
    -0.26
     éc
    -0.25
     propag
    -0.25
     Mull
    -0.25
    isl
    -0.25
    asing
    -0.25
    POSITIVE LOGITS
    èĨĺ
    0.26
    ][(
    0.26
    åĴĮæĬĢæľ¯
    0.25
    [ix
    0.25
    Ix
    0.25
    èĥĻ
    0.25
    注æĺİæĿ¥æºIJ
    0.25
    çļĦçĶ»éĿ¢
    0.25
     venue
    0.24
    欲
    0.24
    Activations Density 0.991%

    No Known Activations