© 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. 41860
    Prev
    Next
    INDEX
    Explanations

    say [the ending -ot, -ore, -ores, -ologist, -oscope]

    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
     dai
    -0.28
     dép
    -0.26
     du
    -0.26
    él
    -0.25
     Ned
    -0.24
    ctime
    -0.24
     LoginPage
    -0.24
    çĪ±äºº
    -0.24
     lid
    -0.23
    å¼Ģåħĥ
    -0.23
    POSITIVE LOGITS
    ot
    0.30
    Cong
    0.29
    é£İåħī
    0.28
    OT
    0.28
     Cong
    0.28
    èģļ
    0.27
     Paran
    0.27
    ä¼ĺåĬ¿
    0.26
    _stdio
    0.26
    Ø´Ùħ
    0.26
    Activations Density 0.004%

    No Known Activations