© 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. 35-TRANSCODER-HP
    7. 38717
    Prev
    Next
    INDEX
    Explanations

    Ps

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_35.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.35.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    alm
    -0.32
    /OR
    -0.27
    earn
    -0.27
    obe
    -0.27
    ÑįÑĤомÑĥ
    -0.27
    alar
    -0.27
    ifting
    -0.26
    ono
    -0.26
    asta
    -0.26
    kim
    -0.25
    POSITIVE LOGITS
     pose
    0.32
    .nextToken
    0.28
    pose
    0.26
    åIJ§
    0.26
     globe
    0.26
    Pose
    0.25
     poses
    0.25
     goal
    0.25
     warm
    0.25
     global
    0.24
    Activations Density 10.345%

    No Known Activations