© 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. 22-TRANSCODER-HP
    7. 97474
    Prev
    Next
    INDEX
    Explanations

    Belief/opinion

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_22.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.22.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    _manifest
    -0.28
    ilos
    -0.27
    æ±ĭ
    -0.27
     threads
    -0.26
    æ½ľ
    -0.25
    å¾Īæ·±
    -0.25
    acements
    -0.25
    manifest
    -0.24
     jumper
    -0.24
    .Manifest
    -0.24
    POSITIVE LOGITS
    åıªè¦ģæľī
    0.27
    åĨįéĢł
    0.25
    å¿Ĺ
    0.25
    åľ¨è¿ĩåİ»
    0.25
     Phill
    0.24
    ñe
    0.24
    饱
    0.24
    æīĢä»¥åľ¨
    0.24
     anytime
    0.24
    åIJĮæł·çļĦ
    0.24
    Activations Density 0.005%

    No Known Activations