© 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. 39448
    Prev
    Next
    INDEX
    Explanations

    UV radiation and copyright

    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
    зеÑĢ
    -0.31
     eventually
    -0.28
    åIJįçīĮ
    -0.27
    )::
    -0.27
    åĪ¹
    -0.25
     irres
    -0.25
    ðŁijī
    -0.25
    åı¦ä¸Ģ个
    -0.25
    èĥ½æī¾åĪ°
    -0.25
     def
    -0.25
    POSITIVE LOGITS
    èĢķ
    0.30
     themselves
    0.27
    illary
    0.26
    unbind
    0.26
    OWN
    0.26
    ONENT
    0.25
    Stride
    0.25
    unnel
    0.24
     observer
    0.24
     dangling
    0.24
    Activations Density 1.087%

    No Known Activations