© 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. 41748
    Prev
    Next
    INDEX
    Explanations

    Describing something and its passage

    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
    ös
    -0.30
     маÑģÑĤ
    -0.29
    éģ£
    -0.29
     eventually
    -0.29
    .vo
    -0.28
     finally
    -0.27
     ден
    -0.24
    issa
    -0.24
    ç»Īäºİ
    -0.24
    åıĹæįŁ
    -0.24
    POSITIVE LOGITS
     advance
    0.29
    EE
    0.27
    çĭIJ
    0.27
    æ°¸ä¸į
    0.26
    çĶŁæŃ»
    0.26
    roach
    0.25
     cooperating
    0.25
    çIJĨ
    0.24
    critical
    0.24
    clude
    0.24
    Activations Density 0.172%

    No Known Activations