© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 18-TRANSCODER-HP
    7. 88275
    Prev
    Next
    INDEX
    Explanations

    Video content

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_18.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.18.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    agi
    -0.30
    çķĪ
    -0.29
    驱
    -0.28
     Zap
    -0.26
    çĪ¬
    -0.25
    æĬ¥è®°èĢħ
    -0.25
    åį«çĶŁ
    -0.25
     JObject
    -0.25
    ÑĤÑĭ
    -0.24
    空æ°Ķ
    -0.24
    POSITIVE LOGITS
    缸è¾ĥäºİ
    0.27
    vo
    0.25
    play
    0.25
    lua
    0.25
     instant
    0.24
    çħ
    0.24
    instant
    0.24
     highlight
    0.24
    ĥģ
    0.23
    sher
    0.23
    Activations Density 2.037%

    No Known Activations