© 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. 23-TRANSCODER-HP
    7. 24716
    Prev
    Next
    INDEX
    Explanations

    instructions and application

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_23.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.23.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ì¶ķ
    -0.28
    =pos
    -0.27
    æĬ½
    -0.25
    =index
    -0.25
    Ware
    -0.24
    ileo
    -0.24
     ме
    -0.24
    acha
    -0.24
    údo
    -0.24
    æĭĽèĤ¡
    -0.23
    POSITIVE LOGITS
    大大å°ı
    0.30
     carbs
    0.28
     whereabouts
    0.28
    æ¯ı次
    0.28
    鸾
    0.27
    lip
    0.27
     indiv
    0.26
    æ¯ı次éĥ½
    0.26
    å½Ĵå±ŀ
    0.26
    utable
    0.26
    Activations Density 0.001%

    No Known Activations