© 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. 14-TRANSCODER-HP
    7. 40473
    Prev
    Next
    INDEX
    Explanations

    Reinforcement, documents, technical texts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_14.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.14.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Cruiser
    -0.25
    AFF
    -0.25
    ê³łìļĶ
    -0.24
    åĬ¨å·¥
    -0.24
    主ä¸ļ
    -0.23
    .Groups
    -0.23
    æŀģ大
    -0.23
    _RDONLY
    -0.23
    osite
    -0.23
    åĨ
    -0.23
    POSITIVE LOGITS
     {}\
    0.31
    ({},
    0.26
    éĤĭ
    0.25
     PARTY
    0.25
    .pres
    0.24
    -che
    0.24
    айн
    0.24
    æľ¬èº«
    0.24
    .IsActive
    0.24
     speaker
    0.24
    Activations Density 0.126%

    No Known Activations