© 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. 33-TRANSCODER-HP
    7. 52710
    Prev
    Next
    INDEX
    Explanations

    non-English words

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_33.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.33.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     scn
    -0.30
    zac
    -0.29
    me
    -0.28
    zm
    -0.28
    cce
    -0.28
    -Tr
    -0.28
    dcc
    -0.27
    mir
    -0.26
    tr
    -0.26
    deg
    -0.26
    POSITIVE LOGITS
    饶
    0.28
    å²Ń
    0.26
    веден
    0.26
    çĶ³è¯·äºº
    0.25
    unk
    0.24
    usted
    0.24
    pread
    0.23
    çĥŃ线
    0.23
    ç³Ł
    0.23
    ruk
    0.23
    Activations Density 0.014%

    No Known Activations