© 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. 27-TRANSCODER-HP
    7. 58557
    Prev
    Next
    INDEX
    Explanations

    z

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_27.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.27.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    untime
    -0.27
    (layers
    -0.26
    ãĤ¬ãĤ¤
    -0.25
     Tubes
    -0.25
     Leaves
    -0.25
     Franz
    -0.24
    éĥ¨ä¸»ä»»
    -0.24
    æīģ
    -0.24
    assin
    -0.24
    EDIT
    -0.24
    POSITIVE LOGITS
     recovering
    0.28
     recover
    0.27
     recovery
    0.26
    bral
    0.25
     ex
    0.24
    çģ¶
    0.24
    åŁł
    0.24
     SPACE
    0.23
    eb
    0.23
     recovered
    0.23
    Activations Density 0.000%

    No Known Activations