© 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. 25582
    Prev
    Next
    INDEX
    Explanations

    Lamb

    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
    agus
    -0.26
     glo
    -0.25
    éĹ¾
    -0.25
    ittel
    -0.25
    ulsion
    -0.24
    èµĥ
    -0.24
    éĩijçīĮ
    -0.24
    GN
    -0.24
     Murphy
    -0.23
     filt
    -0.23
    POSITIVE LOGITS
    lands
    0.26
    iations
    0.25
    ing
    0.24
    yw
    0.24
    others
    0.24
    æ°¸
    0.24
    еÑģп
    0.24
    า
    0.24
    aldi
    0.23
     intox
    0.23
    Activations Density 0.073%

    No Known Activations