© 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. 95727
    Prev
    Next
    INDEX
    Explanations

    str

    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
    ä¸Ī
    -0.29
    äºĤ
    -0.27
     thick
    -0.26
    碳
    -0.26
    carbon
    -0.26
    çĿĢçľ¼
    -0.26
    ünde
    -0.25
    ired
    -0.25
    mare
    -0.24
    ä¹±
    -0.24
    POSITIVE LOGITS
    ophil
    0.30
    ÅĤaw
    0.27
     bask
    0.26
    .items
    0.25
     Buch
    0.25
    ristol
    0.25
     szcz
    0.24
     Items
    0.24
     itens
    0.24
     portrait
    0.23
    Activations Density 0.016%

    No Known Activations