© 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. 95202
    Prev
    Next
    INDEX
    Explanations

    Cost of living

    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
    önü
    -0.30
    _payload
    -0.29
    utches
    -0.24
    èĹ©
    -0.24
     famine
    -0.24
     Pav
    -0.24
    Intent
    -0.24
     кап
    -0.24
    æ½ŀ
    -0.24
    æºī
    -0.24
    POSITIVE LOGITS
     cost
    0.50
    çĶŁæ´»
    0.49
    cost
    0.48
     Cost
    0.46
    living
    0.41
     QS
    0.40
     living
    0.40
    Cost
    0.40
    _cost
    0.40
    çĶŁæ´»è´¨éĩı
    0.39
    Activations Density 1.459%

    No Known Activations