© 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. 41710
    Prev
    Next
    INDEX
    Explanations

    costs, legality, rights

    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
    Negative Logits
    è®¤çľŁ
    -0.30
    oration
    -0.28
    orative
    -0.26
    åħ¢
    -0.26
     micro
    -0.25
    ä¸Ģèµ·åİ»
    -0.25
    æ¡Įä¸Ĭ
    -0.25
    aho
    -0.25
    èªį
    -0.25
    formation
    -0.25
    POSITIVE LOGITS
    ÃŃc
    0.26
    Ĩµ
    0.25
    ][:
    0.24
    ONA
    0.24
    )("
    0.23
     spread
    0.23
    ift
    0.23
    ovan
    0.23
    FTA
    0.23
     :=
    0.23
    Activations Density 2.320%

    No Known Activations