© 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. 96847
    Prev
    Next
    INDEX
    Explanations

    sun/solar activity

    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
    溱
    -0.25
    igi
    -0.24
    igue
    -0.24
    åħĶ
    -0.24
     Programme
    -0.23
    ế
    -0.23
    ç»ħ
    -0.23
    è¡¡
    -0.23
     Basket
    -0.23
    verte
    -0.23
    POSITIVE LOGITS
     sun
    0.30
     solar
    0.30
     bursts
    0.29
    太éĺ³
    0.29
     Explosion
    0.28
    èĩ´åij½
    0.28
    sun
    0.28
     matter
    0.28
    getVar
    0.28
     bright
    0.28
    Activations Density 0.885%

    No Known Activations