© 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. 32-TRANSCODER-HP
    7. 43136
    Prev
    Next
    INDEX
    Explanations

    say "the ending -iated"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_32.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.32.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    çļĦè¶ĭåĬ¿
    -0.28
    ém
    -0.27
    gee
    -0.27
    isé
    -0.26
    NSS
    -0.25
    çIJĨ
    -0.24
    oref
    -0.24
    urally
    -0.24
    Fred
    -0.23
    eries
    -0.23
    POSITIVE LOGITS
    cheid
    0.32
    kte
    0.28
    iazza
    0.28
    æļ´
    0.28
    uite
    0.26
    utable
    0.26
    tar
    0.26
    acin
    0.26
     Macron
    0.25
    -place
    0.25
    Activations Density 0.001%

    No Known Activations