© 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. 58603
    Prev
    Next
    INDEX
    Explanations

    never

    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
    stown
    -0.31
    cess
    -0.28
    å¾ħ
    -0.26
     airflow
    -0.26
    cco
    -0.25
     reminded
    -0.25
     overwhel
    -0.25
     Availability
    -0.25
     defaults
    -0.24
     Levine
    -0.24
    POSITIVE LOGITS
    ever
    0.27
    StringUtil
    0.27
    _Impl
    0.26
     ever
    0.24
    -ever
    0.24
    æݥ触åĪ°
    0.24
    第äºĮ天
    0.24
    theless
    0.24
    throp
    0.23
    optgroup
    0.23
    Activations Density 0.009%

    No Known Activations