© 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. 30-TRANSCODER-HP
    7. 95243
    Prev
    Next
    INDEX
    Explanations

    software or code context

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_30.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.30.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    plex
    -0.31
     hindsight
    -0.27
    Ind
    -0.27
    è°Ī
    -0.26
    åĨ¶éĩij
    -0.26
     Ind
    -0.25
    divide
    -0.24
     ind
    -0.24
    indx
    -0.24
    èĢģåħµ
    -0.24
    POSITIVE LOGITS
    URY
    0.29
     Docs
    0.29
    docs
    0.28
    amy
    0.26
    lie
    0.26
     Gh
    0.26
    -controls
    0.25
    æĴ¬
    0.25
    -fr
    0.24
     letters
    0.24
    Activations Density 0.782%

    No Known Activations