© 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. 24-TRANSCODER-HP
    7. 149168
    Prev
    Next
    INDEX
    Explanations

    neither

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_24.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.24.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     isn
    -0.28
    lide
    -0.27
    ç¼ī
    -0.25
    ibles
    -0.25
     REM
    -0.25
    ivism
    -0.24
    å¼ĤæĢ§
    -0.24
    âī»
    -0.24
    rapy
    -0.24
    顺
    -0.23
    POSITIVE LOGITS
    true
    0.28
    UpDown
    0.27
    .Invariant
    0.27
    å§IJ妹
    0.26
    æŃĩ
    0.26
    theless
    0.25
    emies
    0.25
    ä¸Ĭä¸ĭ游
    0.24
    xon
    0.24
    èĩŁ
    0.24
    Activations Density 0.164%

    No Known Activations