© 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. 108206
    Prev
    Next
    INDEX
    Explanations

    technical contexts and numbers

    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
     companies
    -0.48
    ä¼ģä¸ļ
    -0.46
    åķĨ家
    -0.44
    åħ¬åı¸
    -0.44
    ä¼ģä¸ļçļĦ
    -0.41
     corporate
    -0.41
     corporations
    -0.40
     employers
    -0.40
    åİĤåķĨ
    -0.40
     businesses
    -0.39
    POSITIVE LOGITS
    arry
    0.28
    ForObject
    0.26
    esModule
    0.26
    女ãģ®åŃIJ
    0.26
    å®ŀäºĭ
    0.26
    arians
    0.25
    èĬ¦
    0.25
    _mob
    0.25
    å²ģ以ä¸Ĭ
    0.25
    ,function
    0.25
    Activations Density 1.001%

    No Known Activations