© 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. 30-TRANSCODER-HP
    7. 94883
    Prev
    Next
    INDEX
    Explanations

    lat

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_30.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.30.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    abor
    -0.27
     caret
    -0.25
    enberg
    -0.25
     paren
    -0.25
    eor
    -0.25
    两级
    -0.24
    wald
    -0.24
    awl
    -0.24
    ÑĢам
    -0.24
    .rs
    -0.23
    POSITIVE LOGITS
    ewis
    0.31
    ENT
    0.28
    Mut
    0.27
    ä½ĵçİ°
    0.26
    åħħåĪĨä½ĵçİ°
    0.26
    èIJ½åľ°
    0.26
    åĬ¨
    0.26
    енÑĤ
    0.26
    isser
    0.25
    atedRoute
    0.25
    Activations Density 0.103%

    No Known Activations