© 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. 161738
    Prev
    Next
    INDEX
    Explanations

    Date ranges

    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
    çĨŁ
    -0.29
    象
    -0.26
    ov
    -0.26
    èµ°åIJij
    -0.25
    icates
    -0.25
    ustria
    -0.25
    oc
    -0.25
    âĶ´
    -0.24
    æ³¥
    -0.24
    agrams
    -0.24
    POSITIVE LOGITS
    éķĶ
    0.28
    lei
    0.27
    两æīĭ
    0.26
    bach
    0.26
     Elm
    0.25
     surrounding
    0.25
     forcibly
    0.25
    groupName
    0.25
    HasBeen
    0.25
    褫
    0.24
    Activations Density 0.011%

    No Known Activations