© 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. 32-TRANSCODER-HP
    7. 40935
    Prev
    Next
    INDEX
    Explanations

    Technical and documentation texts

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_32.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.32.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    unal
    -0.27
    illas
    -0.24
    ầy
    -0.24
    hashCode
    -0.24
    rimp
    -0.23
     PH
    -0.23
     FW
    -0.23
    ughs
    -0.23
    wt
    -0.22
     SMP
    -0.22
    POSITIVE LOGITS
    babel
    0.27
    bil
    0.26
     skill
    0.26
     skl
    0.25
     accompany
    0.25
    çĨ¨
    0.25
    æĬĢèĥ½
    0.24
    skill
    0.24
    iams
    0.24
    sing
    0.24
    Activations Density 0.000%

    No Known Activations