© 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. 25-TRANSCODER-HP
    7. 107081
    Prev
    Next
    INDEX
    Explanations

    man

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_25.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.25.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    夹
    -0.26
    stress
    -0.26
     ind
    -0.24
     brig
    -0.24
    æĿłæĿĨ
    -0.23
    ingers
    -0.23
    ¿
    -0.23
    ä¸ºçĽ®æłĩ
    -0.23
    åĪĹ
    -0.23
     "("
    -0.23
    POSITIVE LOGITS
     Rew
    0.29
    ầu
    0.25
    ModelError
    0.25
    ersed
    0.25
    reated
    0.24
    à¸Ĭะ
    0.24
    rition
    0.24
     Poison
    0.24
     Beste
    0.23
    SelfPermission
    0.23
    Activations Density 0.030%

    No Known Activations