© 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. 23-TRANSCODER-HP
    7. 24435
    Prev
    Next
    INDEX
    Explanations

    enforce

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_23.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.23.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     diplom
    -0.27
    tır
    -0.26
    apult
    -0.26
    sheets
    -0.26
    ç°§
    -0.26
    åıijçĥ§
    -0.25
    çĬĬ
    -0.24
    s
    -0.24
    sstream
    -0.23
    eker
    -0.23
    POSITIVE LOGITS
     enforce
    0.35
     enforced
    0.32
     written
    0.31
    éķ°
    0.30
     strict
    0.29
     enforcing
    0.29
     compliance
    0.29
     enforcement
    0.28
    ied
    0.27
     restrictions
    0.27
    Activations Density 0.019%

    No Known Activations