© 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. 56806
    Prev
    Next
    INDEX
    Explanations

    ring

    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
    loo
    -0.31
    åĦĨ
    -0.28
    adro
    -0.25
    amment
    -0.25
    å¾ĹçĽĬ
    -0.25
    å²ģ以ä¸ĭ
    -0.25
    身å¿ĥåģ¥åº·
    -0.24
    ultiple
    -0.24
     fib
    -0.24
     rational
    -0.24
    POSITIVE LOGITS
     ring
    0.36
    çݯ
    0.36
     rings
    0.35
    -ring
    0.34
     Rings
    0.33
    RING
    0.31
    çĴ°
    0.29
     hoops
    0.27
    CRY
    0.27
    _RING
    0.26
    Activations Density 0.049%

    No Known Activations