© 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. 30-TRANSCODER-HP
    7. 96008
    Prev
    Next
    INDEX
    Explanations

    durability and resilience

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_30.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.30.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    åĿļ强
    -0.39
    ç¨³åĽº
    -0.38
     Survival
    -0.37
     robust
    -0.36
    稳åģ¥
    -0.35
    稳
    -0.34
    åĿļ
    -0.33
     reinforcement
    -0.32
     survival
    -0.32
    rob
    -0.32
    POSITIVE LOGITS
     against
    0.30
    iod
    0.28
    contributors
    0.27
    fällig
    0.27
    qualities
    0.27
    yclic
    0.26
    lijk
    0.26
     Inf
    0.25
    ouden
    0.25
     qualities
    0.24
    Activations Density 0.026%

    No Known Activations