© 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. 39707
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    票
    -0.29
    ve
    -0.29
     remain
    -0.27
    ert
    -0.27
    urge
    -0.26
     tickets
    -0.26
    uls
    -0.25
    SEA
    -0.25
    çĽĨ
    -0.25
    åħĥå·¦åı³
    -0.25
    POSITIVE LOGITS
     Ngb
    0.26
    è¯Ĭ
    0.25
    ä»»åĬ¡
    0.25
    дÑĭ
    0.25
    (act
    0.24
    (Task
    0.24
    èĩªè§ī
    0.24
    amient
    0.23
    .nz
    0.23
    (task
    0.23
    Activations Density 0.116%

    No Known Activations

    This feature has no known activations.