© 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. 23-TRANSCODER-HP
    7. 23402
    Prev
    Next
    INDEX
    Explanations

    Named entities

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_23.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.23.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    çĽĶ
    -0.31
    åħ¶ä¸Ńä¹ĭä¸Ģ
    -0.30
    enuous
    -0.27
    æĸĹ
    -0.26
    çī¢
    -0.26
    éħ£
    -0.26
    ãĥĥãĥĦ
    -0.25
    .club
    -0.25
    æ·±åħ¥
    -0.25
    èĩªæĿ¥
    -0.25
    POSITIVE LOGITS
    fore
    0.25
    ?family
    0.24
    AccessException
    0.24
     Robots
    0.24
     Aware
    0.24
    aci
    0.24
    weg
    0.23
    å®īåħ¨éļIJæĤ£
    0.23
    amples
    0.23
    zie
    0.23
    Activations Density 0.004%

    No Known Activations