© 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. 44244
    Prev
    Next
    INDEX
    Explanations

    ,

    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
    åĶ§
    -0.30
    isci
    -0.28
    Inc
    -0.27
    alc
    -0.27
    plr
    -0.26
    mares
    -0.26
     MSS
    -0.26
     Inc
    -0.26
    lice
    -0.26
     Sabb
    -0.25
    POSITIVE LOGITS
    ainting
    0.28
    _bulk
    0.28
    ibe
    0.26
    å±ħ
    0.26
    arm
    0.25
    ring
    0.24
    éĥ½èĥ½å¤Ł
    0.24
    /core
    0.24
    bulk
    0.24
    reau
    0.24
    Activations Density 0.000%

    No Known Activations