© 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. 30-TRANSCODER-HP
    7. 96181
    Prev
    Next
    INDEX
    Explanations

    pin

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_30.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.30.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ITO
    -0.27
    çĻ¾åĪĨ
    -0.26
    sj
    -0.26
    нак
    -0.26
    irma
    -0.25
    .backward
    -0.25
    irts
    -0.25
    ıt
    -0.25
    å±Ĥ次
    -0.24
    Ø´ÙĪ
    -0.24
    POSITIVE LOGITS
    读èĢħ
    0.32
    éĴĪ
    0.29
    è§Ĥä¼Ĺ
    0.28
     definition
    0.28
     suite
    0.27
     reader
    0.27
    å®ļä¹ī
    0.27
    ока
    0.26
    dee
    0.26
     Header
    0.26
    Activations Density 0.886%

    No Known Activations