© 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. 9927
    Prev
    Next
    INDEX
    Explanations

    technical and formal texts

    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
    (transform
    -0.26
     suffice
    -0.26
    ãģ¤ãģ®
    -0.26
     scratches
    -0.25
    /lists
    -0.25
     supply
    -0.25
    AsStream
    -0.24
     Prosec
    -0.24
    ismatic
    -0.24
     blacklist
    -0.24
    POSITIVE LOGITS
    çĽĺ
    0.27
    Integral
    0.26
     "</
    0.26
     dis
    0.26
    对该
    0.25
    eam
    0.25
    Ĥ¬
    0.25
    åĴķ
    0.25
    缸åıį
    0.25
    otropic
    0.25
    Activations Density 0.000%

    No Known Activations