© 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. 31-TRANSCODER-HP
    7. 18600
    Prev
    Next
    INDEX
    Explanations

    Question/answer and code snippets

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_31.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.31.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     nom
    -0.37
    n
    -0.35
     n
    -0.34
    ^n
    -0.32
    _n
    -0.30
     nib
    -0.30
    nom
    -0.30
    nob
    -0.29
     nob
    -0.28
    nÃŃ
    -0.28
    POSITIVE LOGITS
    è¶Ĭ
    0.27
    leaders
    0.26
    raises
    0.25
     SIDE
    0.25
    berger
    0.25
    çĶĦ
    0.25
    ä¸Ģ个å¤ļ
    0.24
    å«ļ
    0.24
    ilage
    0.24
    oker
    0.23
    Activations Density 1.853%

    No Known Activations