© 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. 20-TRANSCODER-HP
    7. 141328
    Prev
    Next
    INDEX
    Explanations

    problem solving

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_20.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.20.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    aram
    -0.27
    ëĭ¨
    -0.26
    Ģ
    -0.26
    çīĪæĿĥ声æĺİ
    -0.26
    ivar
    -0.26
     standard
    -0.25
    arem
    -0.24
    inh
    -0.24
     ret
    -0.24
    çī¹
    -0.24
    POSITIVE LOGITS
     mutate
    0.26
    (mut
    0.25
     recurs
    0.25
    fusion
    0.25
    beat
    0.25
    ä¸ĢæŶ
    0.25
    _sur
    0.25
     fusion
    0.25
    Destroyed
    0.24
    å¤įèĭı
    0.24
    Activations Density 24.168%

    No Known Activations