© 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. 52654
    Prev
    Next
    INDEX
    Explanations

    er

    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
     stoi
    -0.29
     bloom
    -0.27
    onis
    -0.26
    æİ·
    -0.26
    å¼¹
    -0.26
    Blob
    -0.25
    aN
    -0.25
    ä»İä¸Ń
    -0.25
    Ñģкоп
    -0.25
    _literals
    -0.24
    POSITIVE LOGITS
     er
    0.65
    .er
    0.45
     dis
    0.44
    _er
    0.41
     ER
    0.40
     fr
    0.40
    er
    0.40
    ér
    0.39
    å°Ķ
    0.37
     cr
    0.36
    Activations Density 0.172%

    No Known Activations