© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 23-TRANSCODER-HP
    7. 161992
    Prev
    Next
    INDEX
    Explanations

    jobs and professions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_23.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.23.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¦Ī
    -0.29
    cased
    -0.28
    ernel
    -0.27
    媽
    -0.26
    æ·±å¤Ħ
    -0.26
    åĩ¿
    -0.26
    çĿĢçľ¼
    -0.25
    ading
    -0.25
     Dame
    -0.24
    acher
    -0.24
    POSITIVE LOGITS
    kip
    0.32
    dl
    0.26
    istar
    0.25
    clip
    0.24
    å²Ĺä½į
    0.24
     braz
    0.24
    è¶ĬæĿ¥
    0.23
    èłķ
    0.23
    ç§Ģ
    0.23
    å¤įåĪ¶
    0.23
    Activations Density 0.010%

    No Known Activations