© 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. 108941
    Prev
    Next
    INDEX
    Explanations

    was

    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
    ä¼ļ被
    -0.28
    人æ°ijæ³ķéĻ¢
    -0.26
    åıĪ被
    -0.25
    em
    -0.25
    æĪ³
    -0.25
     caut
    -0.24
    çŁ³å®¶
    -0.24
     karma
    -0.24
     Kemp
    -0.24
    Throwable
    -0.24
    POSITIVE LOGITS
    bü
    0.27
    ç®±
    0.26
    纳
    0.25
    eyed
    0.24
     graduate
    0.23
    æķĪ
    0.23
    .verbose
    0.23
    å´Ń
    0.23
     succeeding
    0.23
    identally
    0.22
    Activations Density 1.378%

    No Known Activations