© 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. 27-TRANSCODER-HP
    7. 9863
    Prev
    Next
    INDEX
    Explanations

    scientific papers

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_27.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.27.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    çļĦæĥħåĨµ
    -0.33
    è¿Ļç§įæĥħåĨµ
    -0.32
    çĬ¶åĨµ
    -0.31
    çļĦçݰ象
    -0.31
    çĹĩçĬ¶
    -0.31
     conditions
    -0.26
     circumstance
    -0.25
     symptoms
    -0.25
    /audio
    -0.25
    çļĦæĥħå½¢
    -0.25
    POSITIVE LOGITS
     hott
    0.30
     ips
    0.27
     mud
    0.27
    moid
    0.26
    igua
    0.26
    xis
    0.25
    uxt
    0.25
    utr
    0.25
     cle
    0.24
    ipline
    0.24
    Activations Density 0.028%

    No Known Activations