© 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. 97087
    Prev
    Next
    INDEX
    Explanations

    4

    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
    Negative Logits
     Ear
    -0.27
    åłĤ
    -0.26
    缨
    -0.25
    =device
    -0.24
     Gut
    -0.24
    avar
    -0.24
    é»ijå¤ľ
    -0.24
    erte
    -0.24
     spreading
    -0.23
     gut
    -0.23
    POSITIVE LOGITS
    éĴĭ
    0.28
     Side
    0.28
    phis
    0.27
    masters
    0.26
    markets
    0.25
     Sisters
    0.25
    Side
    0.24
    å§Ĭ妹
    0.24
    èĴ
    0.24
    缸è§ģ
    0.24
    Activations Density 0.783%

    No Known Activations