© 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. 27-TRANSCODER-HP
    7. 9756
    Prev
    Next
    INDEX
    Explanations

    Research or project names

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_27.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.27.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     central
    -0.29
     Central
    -0.28
    çĺĹ
    -0.25
    central
    -0.25
    Central
    -0.25
    tolower
    -0.25
    ota
    -0.25
     lan
    -0.25
    rz
    -0.24
    .hostname
    -0.24
    POSITIVE LOGITS
     scrim
    0.32
     Sisters
    0.29
     cram
    0.28
    zens
    0.26
    æĸ°æł¼å±Ģ
    0.26
    éļľ
    0.26
    éĺħ读
    0.26
     feminism
    0.26
    è¡¡
    0.26
    elter
    0.25
    Activations Density 0.000%

    No Known Activations