© 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. 8835
    Prev
    Next
    INDEX
    Explanations

    Beginning of formal document

    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
    ãģĹãģ°
    -0.29
    HT
    -0.29
    GetObject
    -0.27
    elon
    -0.27
    å±Ģéķ¿
    -0.26
    æ¯Ķäºļ
    -0.26
    /order
    -0.26
     chac
    -0.26
     consistently
    -0.25
    Anth
    -0.25
    POSITIVE LOGITS
    à²ļ
    0.28
    åĩºæ±Ĺ
    0.27
     realization
    0.26
     fireworks
    0.26
     помоÑīи
    0.26
    æĦıä¹īä¸Ĭ
    0.25
     sides
    0.25
     master
    0.24
    çĹĺ
    0.24
    帮
    0.24
    Activations Density 0.000%

    No Known Activations