© 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. 96785
    Prev
    Next
    INDEX
    Explanations

    Technical documents or parsing errors

    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
    åįģåħ«
    -0.31
    ä¸ĥ
    -0.31
    åįģä¸ĥ
    -0.30
    -eight
    -0.30
     seventh
    -0.29
     eighth
    -0.29
     eight
    -0.28
     seven
    -0.27
    åħ«
    -0.27
     fourteen
    -0.26
    POSITIVE LOGITS
    pow
    0.30
    æĹ©æľŁ
    0.28
    æĹłæĥħ
    0.28
    (pow
    0.27
    -addons
    0.26
    æĶ¶
    0.26
     Early
    0.25
    æĮ¹
    0.25
    æ·ĭ
    0.25
     pow
    0.25
    Activations Density 0.101%

    No Known Activations