© 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. 30-TRANSCODER-HP
    7. 95259
    Prev
    Next
    INDEX
    Explanations

    Humidity and moisture

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_30.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.30.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     dry
    -1.52
    å¹²
    -1.45
    å¹²çĩ¥
    -1.40
     drying
    -1.34
    dry
    -1.29
    Dry
    -1.28
     dried
    -1.27
     Dry
    -1.24
    ä¹¾
    -1.22
     dryer
    -1.10
    POSITIVE LOGITS
    usses
    0.25
     Bir
    0.25
    èī¯å¿ĥ
    0.24
    [group
    0.23
    ksen
    0.23
    亲æīĭ
    0.23
     Belfast
    0.23
    BER
    0.23
    ccount
    0.23
     folk
    0.22
    Activations Density 0.903%

    No Known Activations