© 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. 24-TRANSCODER-HP
    7. 150410
    Prev
    Next
    INDEX
    Explanations

    Foreign words

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_24.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.24.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¸¥æł¼æĮīçħ§
    -0.28
    cessive
    -0.26
    ä»ĭ
    -0.26
    éĻIJè´Ń
    -0.25
    umbo
    -0.25
    [end
    -0.25
    ä½ľæĸĩ
    -0.25
    ại
    -0.25
    å°
    -0.24
    æłħ
    -0.24
    POSITIVE LOGITS
    yen
    0.25
    æīijåħĭ
    0.24
    érica
    0.23
     Mercer
    0.23
     peace
    0.23
     Still
    0.23
     still
    0.23
    TRL
    0.23
     doubt
    0.23
    åIJ¦åĪĻ
    0.23
    Activations Density 0.098%

    No Known Activations