© 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. 96228
    Prev
    Next
    INDEX
    Explanations

    equality

    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
    other
    -0.41
     other
    -0.37
    åħ¶ä»ĸçļĦ
    -0.35
    (other
    -0.31
    .other
    -0.31
    åħ¶ä»ĸ人
    -0.30
    åħ¶ä»ĸ
    -0.30
    OTHER
    -0.29
    such
    -0.29
    whether
    -0.29
    POSITIVE LOGITS
     equal
    0.43
     Equal
    0.40
     equals
    0.38
    equ
    0.38
     everywhere
    0.38
     equally
    0.36
    Equ
    0.35
    Equal
    0.35
     equality
    0.34
     Equ
    0.34
    Activations Density 0.895%

    No Known Activations