© 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. 12-TRANSCODER-HP
    7. 22313
    Prev
    Next
    INDEX
    Explanations

    Strength/weakness

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_12.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.12.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    顺
    -0.26
    éģŃéģĩ
    -0.26
    dition
    -0.26
    Fa
    -0.25
    abet
    -0.24
    Fit
    -0.24
    åºĵåŃĺ
    -0.24
    å«ģ
    -0.24
    iktig
    -0.23
    >č↵
    -0.23
    POSITIVE LOGITS
     newRow
    0.28
    è³ĩ
    0.28
    èµĦ
    0.27
     getById
    0.26
    دة
    0.26
    端æŃ£
    0.26
    åķĦ
    0.25
     Reds
    0.25
    leaf
    0.25
    lets
    0.25
    Activations Density 0.006%

    No Known Activations