© 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. 27-TRANSCODER-HP
    7. 57355
    Prev
    Next
    INDEX
    Explanations

    deaths and injuries

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_27.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.27.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    以èī²
    -0.30
    æ´ģçĻ½
    -0.27
    èĬ±æł·
    -0.26
     teach
    -0.25
    åī©ä¸ĭ
    -0.24
    è¦ģæ±Ĥ
    -0.24
     legalized
    -0.24
    èĤļ
    -0.24
    çķĻ
    -0.24
    é¢Ĩ导ä¸ĭ
    -0.24
    POSITIVE LOGITS
    éĩį伤
    0.35
     casualties
    0.35
    ermo
    0.29
    ä¹ĺ车
    0.29
    æĭ¥åłµ
    0.28
    éģĩéļ¾
    0.28
    åıĹ伤
    0.26
     unavoid
    0.26
    伤亡
    0.26
     beneficiaries
    0.25
    Activations Density 0.004%

    No Known Activations