© 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. 9-TRANSCODER-HP
    7. 29666
    Prev
    Next
    INDEX
    Explanations

    not

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_9.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.9.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    odes
    -0.27
    _Enter
    -0.27
    lyph
    -0.26
    icles
    -0.26
     internal
    -0.26
    á»ijt
    -0.26
     ///<
    -0.25
     bug
    -0.25
    èµĺ
    -0.25
     bang
    -0.25
    POSITIVE LOGITS
     nto
    0.27
     dee
    0.27
    åł°
    0.25
     Casting
    0.25
    æĬķ
    0.25
    UNIT
    0.24
    éĤ¾
    0.24
    (dep
    0.24
    ä½łèĩªå·±
    0.24
    _NR
    0.24
    Activations Density 1.509%

    No Known Activations