© 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. 161
    Prev
    Next
    INDEX
    Explanations

    names

    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
    ocio
    -0.27
    orst
    -0.26
     latter
    -0.25
     Later
    -0.25
    åĢĴ
    -0.25
     Vit
    -0.24
     somew
    -0.24
    Later
    -0.24
     Cir
    -0.23
    åľ¨å®¶éĩĮ
    -0.23
    POSITIVE LOGITS
    dda
    0.28
    IONS
    0.25
     dạ
    0.25
    éĩįå¤į
    0.24
    erness
    0.23
    -io
    0.23
     dü
    0.23
    æĭ¨
    0.23
     sober
    0.23
    åħ¨ä½ĵ
    0.22
    Activations Density 0.005%

    No Known Activations