© 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. 32-TRANSCODER-HP
    7. 41274
    Prev
    Next
    INDEX
    Explanations

    code and legal rights

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_32.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.32.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     rights
    -0.42
    æĿĥåĪ©
    -0.42
     right
    -0.42
    RIGHT
    -0.41
    right
    -0.38
     RIGHT
    -0.38
     Right
    -0.36
     RIGHTS
    -0.35
    rights
    -0.34
    æ¬ĬåĪ©
    -0.34
    POSITIVE LOGITS
    æŀ¶
    0.25
    ä¸įéĹ´æĸŃ
    0.24
     htmlentities
    0.24
    åIJ«
    0.23
    ä¸Ģéģį
    0.23
    feed
    0.23
    çĶµ
    0.23
    ubre
    0.22
     feed
    0.22
    .lua
    0.22
    Activations Density 0.001%

    No Known Activations