© 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. 111518
    Prev
    Next
    INDEX
    Explanations

    code and math

    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
    iglia
    -0.27
    为æĤ¨
    -0.26
    æ¦ľ
    -0.25
    è¯Ģ
    -0.24
    reservation
    -0.24
     pedig
    -0.24
    PropertyParams
    -0.24
    ç»ĻæĤ¨
    -0.23
    æīĭ
    -0.23
    æĶ¶
    -0.23
    POSITIVE LOGITS
    hum
    0.26
    çĭ¸
    0.26
    ).*
    0.26
     logical
    0.26
    ncy
    0.25
    .fits
    0.25
    ORB
    0.24
     Soros
    0.24
    å¸Ĥä¸Ńå¿ĥ
    0.24
    neg
    0.24
    Activations Density 0.000%

    No Known Activations