© 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. 96937
    Prev
    Next
    INDEX
    Explanations

    smile

    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
    æ³»
    -0.29
    çķ¸
    -0.28
    eman
    -0.26
    夷
    -0.26
     oath
    -0.25
    çĸı
    -0.25
     Man
    -0.25
    éŀĺ
    -0.25
    ega
    -0.25
     MAN
    -0.25
    POSITIVE LOGITS
    ertools
    0.26
    decorators
    0.26
    cmds
    0.26
    常
    0.25
    ody
    0.25
    åľ¨è·¯ä¸Ĭ
    0.25
    antly
    0.24
     plated
    0.24
    alars
    0.24
    endra
    0.24
    Activations Density 0.025%

    No Known Activations