© 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. 14-TRANSCODER-HP
    7. 41465
    Prev
    Next
    INDEX
    Explanations

    numbers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_14.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.14.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     sixth
    -0.28
    æłĩæĺİ
    -0.27
    GetString
    -0.25
    æĬķèµĦ人
    -0.25
     Sixth
    -0.25
    ysize
    -0.24
     Keller
    -0.24
    æĪIJ份
    -0.24
     Clone
    -0.24
    ingly
    -0.23
    POSITIVE LOGITS
    enschaft
    0.27
    å½±è§Ĩåī§
    0.26
    课åłĤæķĻåѦ
    0.26
    çķĻå®Ī
    0.25
    éļľ
    0.24
     declarations
    0.24
    ietf
    0.24
    çĤĬ
    0.24
    è¾ľè´Ł
    0.23
     mou
    0.23
    Activations Density 0.069%

    No Known Activations