© 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. 57340
    Prev
    Next
    INDEX
    Explanations

    Superlative adjectives

    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
    éĤ£æĺ¯
    -0.28
    sons
    -0.27
     $__
    -0.26
    arters
    -0.26
    apsible
    -0.26
    objs
    -0.26
    ä¸Ģç»ı
    -0.25
     ones
    -0.25
    =context
    -0.25
    æľªçŁ¥
    -0.25
    POSITIVE LOGITS
     thing
    0.35
    äºĭæĥħ
    0.31
     things
    0.31
    åģļçļĦäºĭæĥħ
    0.28
    衬
    0.27
     loaf
    0.27
    Positive
    0.27
    ijkl
    0.27
    å¾Īå¤ļäºĭæĥħ
    0.27
    çļĦäºĭæĥħ
    0.26
    Activations Density 0.005%

    No Known Activations