© 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. 107075
    Prev
    Next
    INDEX
    Explanations

    methylation

    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
    éĻĭ
    -0.26
    è¿ĩå¾Ĺ
    -0.25
    rale
    -0.25
     sede
    -0.25
    ELLOW
    -0.24
    лÑı
    -0.24
    loud
    -0.24
    AndPassword
    -0.23
    -background
    -0.23
    erged
    -0.23
    POSITIVE LOGITS
    è¶ħæłĩ
    0.29
    åºĵéĩĮ
    0.29
    critical
    0.28
     critical
    0.27
    licity
    0.26
     accounts
    0.26
    _critical
    0.26
     remover
    0.26
    缸åħ³è§Ħå®ļ
    0.25
     imbalance
    0.25
    Activations Density 0.141%

    No Known Activations