© 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. 4-TRANSCODER-HP
    7. 12
    Prev
    Next
    INDEX
    Explanations

    code lists

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_4.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.4.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ROP
    -0.26
     negative
    -0.26
     lin
    -0.25
    InParameter
    -0.24
     surf
    -0.24
     conditional
    -0.24
    pane
    -0.24
    YE
    -0.24
     lining
    -0.24
    äs
    -0.23
    POSITIVE LOGITS
     Utt
    0.28
    å°ıé¢Ŀ
    0.25
    éķĴ
    0.25
    lish
    0.25
    éĻIJé¢Ŀ
    0.24
    ä¸įè¿ľå¤Ħ
    0.24
    çĺª
    0.24
     stdClass
    0.24
    wares
    0.24
    å¸ĤåĮº
    0.24
    Activations Density 0.083%

    No Known Activations