© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 30-TRANSCODER-HP
    7. 96471
    Prev
    Next
    INDEX
    Explanations

    Code and non-English text

    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
    utely
    -0.26
     Playground
    -0.26
     eu
    -0.26
     gener
    -0.25
    ãĥ¼ãĥł
    -0.25
    é¾
    -0.24
    çİ©åħ·
    -0.24
    imity
    -0.24
    subst
    -0.24
     Rounded
    -0.24
    POSITIVE LOGITS
    æ´»
    0.35
    æī¬
    0.30
    жив
    0.28
    hal
    0.28
    ìĬ¤íĬ¸
    0.27
    æıļ
    0.27
     LiveData
    0.26
    -live
    0.26
    éĢĤ
    0.26
    æŃ¢
    0.25
    Activations Density 0.905%

    No Known Activations