© 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. 89
    Prev
    Next
    INDEX
    Explanations

    baltic

    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
    _IB
    -0.28
    /GPL
    -0.27
    ä¸įæĸŃå®ĮåĸĦ
    -0.26
    amba
    -0.26
     Gilles
    -0.24
    illum
    -0.24
    getDate
    -0.24
    IKE
    -0.24
     libertin
    -0.24
    =back
    -0.24
    POSITIVE LOGITS
     inc
    0.32
    ness
    0.30
    éļ¾
    0.27
    n
    0.27
     inst
    0.26
    鸣
    0.26
     Fam
    0.26
     once
    0.25
     unknown
    0.25
     z
    0.25
    Activations Density 0.015%

    No Known Activations