© 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. 33-TRANSCODER-HP
    7. 52603
    Prev
    Next
    INDEX
    Explanations

    Code and programming contexts

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_33.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.33.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    .Emit
    -0.30
    饥
    -0.28
     uncont
    -0.26
    ubi
    -0.25
    GetInstance
    -0.25
     Vol
    -0.25
    =temp
    -0.24
    æ°¸æģĴ
    -0.24
     emb
    -0.24
    饥饿
    -0.24
    POSITIVE LOGITS
     merc
    0.32
    kom
    0.27
    PAL
    0.26
    enko
    0.26
    merc
    0.26
    æĸ¯é¡¿
    0.25
    rete
    0.25
     Howell
    0.25
     bil
    0.24
    å¹²é¢Ħ
    0.24
    Activations Density 0.017%

    No Known Activations