© 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. 25-TRANSCODER-HP
    7. 106966
    Prev
    Next
    INDEX
    Explanations

    Technical writing/citations

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_25.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.25.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    loff
    -0.29
    plib
    -0.29
    åı£åı·
    -0.28
    ificates
    -0.25
    ÙĦاÙĨ
    -0.24
    ï¼¼
    -0.24
    rollable
    -0.24
    rena
    -0.24
    -fl
    -0.24
    (Of
    -0.23
    POSITIVE LOGITS
    ALS
    0.28
    elihood
    0.27
     Proc
    0.26
     Bliss
    0.25
    ä»İä¸ļ
    0.24
    orks
    0.24
    ç®Ģ便
    0.24
    tür
    0.24
    Marsh
    0.23
    acd
    0.23
    Activations Density 1.041%

    No Known Activations