© 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. 20-TRANSCODER-HP
    7. 62840
    Prev
    Next
    INDEX
    Explanations

    Text snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_20.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.20.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    atively
    -0.30
     traditionally
    -0.26
     repro
    -0.26
    çī¹çĤ¹
    -0.26
     initially
    -0.26
    大èĩ´
    -0.25
     vaguely
    -0.24
     parach
    -0.24
    è·¨
    -0.24
    åİŁåĪĻä¸Ĭ
    -0.24
    POSITIVE LOGITS
    ä¸Ģéĺµ
    0.30
    itti
    0.27
    éĴľ
    0.25
    iego
    0.25
    'aff
    0.24
    iese
    0.24
    å§Ķ
    0.23
    åijĬè¯ī大家
    0.23
    %i
    0.23
     surroundings
    0.23
    Activations Density 79.423%

    No Known Activations