© 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. 27-TRANSCODER-HP
    7. 9036
    Prev
    Next
    INDEX
    Explanations

    the

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_27.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.27.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    bid
    -0.28
    elts
    -0.27
    ĥģ
    -0.26
    elly
    -0.25
    çļĦè¯Ŀé¢ĺ
    -0.25
    DRV
    -0.25
    æķĽ
    -0.25
    pliant
    -0.25
    ä¼Ĭå§ĭ
    -0.24
    IDGE
    -0.24
    POSITIVE LOGITS
     chances
    0.33
     dominance
    0.31
     inertia
    0.29
     stakes
    0.29
    _capacity
    0.28
     rarity
    0.28
    stands
    0.27
     absorption
    0.27
     acceptance
    0.27
    åĩłçİĩ
    0.27
    Activations Density 0.004%

    No Known Activations