© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 25-TRANSCODER-HP
    7. 108828
    Prev
    Next
    INDEX
    Explanations

    Holocaust

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_25.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.25.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    -collapse
    -0.30
    unda
    -0.26
    ç¼ī
    -0.26
    éķ¿å¤§
    -0.26
     shortest
    -0.25
    éĴŀ
    -0.25
    ilan
    -0.24
    æĬĹçĻĮ
    -0.24
    elter
    -0.24
     accum
    -0.24
    POSITIVE LOGITS
    è¿ĻæĿ¡
    0.26
    .ct
    0.26
    交代
    0.25
    igan
    0.24
     abdomen
    0.24
    ee
    0.24
    eras
    0.23
    äºĶå®ĺ
    0.23
    åĽ¾çĶ»
    0.23
     bis
    0.23
    Activations Density 0.965%

    No Known Activations