© 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. 151426
    Prev
    Next
    INDEX
    Explanations

    ]

    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
    ãĤĥ
    -0.27
    omon
    -0.27
     intent
    -0.26
    oste
    -0.24
     lagi
    -0.24
    ãģĹãģĭãģªãģĦ
    -0.23
    ibility
    -0.23
    æijĦ
    -0.23
    å¼ĺ
    -0.23
    ay
    -0.23
    POSITIVE LOGITS
    tÃŃ
    0.25
    Ñĩе
    0.25
     Perfect
    0.24
    hhh
    0.24
    çķĮçļĦ
    0.24
    öh
    0.24
    Perfect
    0.24
    &s
    0.23
    åĻªéŁ³
    0.23
    ipt
    0.23
    Activations Density 0.518%

    No Known Activations