© 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. 32-TRANSCODER-HP
    7. 41754
    Prev
    Next
    INDEX
    Explanations

    is/was statements

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_32.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.32.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    åľºæīĢ
    -0.26
    æĬ½
    -0.26
    大èĦij
    -0.25
    erson
    -0.25
    妤
    -0.24
    两端
    -0.24
    acers
    -0.23
     prem
    -0.23
    人éĥ½
    -0.23
    è·¨è¶Ĭå¼ı
    -0.23
    POSITIVE LOGITS
     word
    0.37
    .word
    0.31
     clearly
    0.28
    æĺİæĺ¾
    0.28
    riet
    0.28
     rõ
    0.28
    æĺİç¡®
    0.28
    rather
    0.27
    	word
    0.27
     rather
    0.27
    Activations Density 0.005%

    No Known Activations