© 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. 41408
    Prev
    Next
    INDEX
    Explanations

    technical writing

    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
    ä¸Ģçīĩ
    -0.28
    pec
    -0.26
    éĩı
    -0.26
    继
    -0.25
    ille
    -0.25
    иÑĢ
    -0.25
    驾驶
    -0.25
    -reset
    -0.24
    端
    -0.24
     HR
    -0.24
    POSITIVE LOGITS
     supervise
    0.28
     fandom
    0.26
    /ion
    0.26
    uno
    0.25
    说起
    0.25
    $self
    0.25
     weakest
    0.25
    æľ¬äºĭ
    0.25
    åĭĸ
    0.24
     {:?}",
    0.24
    Activations Density 0.212%

    No Known Activations