© 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. 25-TRANSCODER-HP
    7. 108406
    Prev
    Next
    INDEX
    Explanations

    link

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_25.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.25.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     FileAccess
    -0.28
     Foster
    -0.26
    foy
    -0.24
    çĿļ
    -0.24
    xdb
    -0.24
    ColumnInfo
    -0.24
     manufactures
    -0.23
    ÑĦÑĤ
    -0.23
    opers
    -0.23
    xFB
    -0.23
    POSITIVE LOGITS
    æĬĦ
    0.30
     copy
    0.30
    copy
    0.30
    	copy
    0.29
     Copy
    0.28
    å¤įåĪ¶
    0.28
    link
    0.28
    ulus
    0.27
    -copy
    0.27
     sources
    0.26
    Activations Density 0.031%

    No Known Activations