© 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. 23689
    Prev
    Next
    INDEX
    Explanations

    geology and rocks

    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
    race
    -0.30
    çļĦ缮åħī
    -0.28
     metals
    -0.27
    éĵĬ
    -0.26
    warf
    -0.26
     kernels
    -0.26
    iron
    -0.26
    çŁ³æĿIJ
    -0.25
    uminium
    -0.25
    éĶĨ
    -0.25
    POSITIVE LOGITS
    à¹Ģà¸Ĺ
    0.26
    èIJ¥éĢł
    0.26
    jsc
    0.26
    uden
    0.25
    thouse
    0.25
    è´¹
    0.24
    (dead
    0.24
    éŃģ
    0.24
     libr
    0.23
    >equals
    0.23
    Activations Density 0.007%

    No Known Activations