© 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. 20-TRANSCODER-HP
    7. 107286
    Prev
    Next
    INDEX
    Explanations

    Technical identifiers/names

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_20.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.20.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     distr
    -0.27
    tere
    -0.26
    ãģĦãģij
    -0.26
    uter
    -0.24
    pled
    -0.24
    ffffff
    -0.24
    ionale
    -0.24
    ogui
    -0.23
    çĦ¶
    -0.23
     BTS
    -0.23
    POSITIVE LOGITS
    Pin
    0.28
    ç¢ľ
    0.26
    artment
    0.25
    _pins
    0.25
    æ©«
    0.25
    横
    0.24
    æīĵæī®
    0.23
    åIJį声
    0.23
     delimited
    0.23
     Pompe
    0.23
    Activations Density 16.501%

    No Known Activations