© 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. 33-TRANSCODER-HP
    7. 53661
    Prev
    Next
    INDEX
    Explanations

    variations of "establish"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_33.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.33.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     RESET
    -0.29
    ftype
    -0.28
     resets
    -0.28
     Resets
    -0.28
    iniz
    -0.26
    ilers
    -0.26
     limp
    -0.26
    ahren
    -0.26
    pis
    -0.25
    brains
    -0.25
    POSITIVE LOGITS
     establishing
    0.29
     establishment
    0.29
     established
    0.29
    aty
    0.27
    establish
    0.27
    ety
    0.27
    èģĺ
    0.26
     AssemblyVersion
    0.26
    æĭĺçķĻ
    0.26
     legal
    0.26
    Activations Density 0.025%

    No Known Activations