© 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. 57710
    Prev
    Next
    INDEX
    Explanations

    code/foreign language

    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
    åĺ´éĩĮ
    -0.26
    emento
    -0.26
    ição
    -0.26
    arine
    -0.25
     Badge
    -0.25
     offence
    -0.25
    å·¡
    -0.25
    esse
    -0.25
    ç¾İå¾·
    -0.25
     hips
    -0.24
    POSITIVE LOGITS
     undercut
    0.27
    semantic
    0.27
    altar
    0.25
    ä¹Łåıªæľī
    0.24
    æĮĩ纹
    0.24
    å°±æѤ
    0.24
    psz
    0.24
     nou
    0.23
    typename
    0.23
    uze
    0.23
    Activations Density 0.004%

    No Known Activations