© 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. 22-TRANSCODER-HP
    7. 87407
    Prev
    Next
    INDEX
    Explanations

    Helping verbs

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_22.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.22.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    toBeDefined
    -0.29
    çļĦæĸ¹å¼ıæĿ¥
    -0.28
     organised
    -0.27
    Hopefully
    -0.27
    -reviewed
    -0.26
     foot
    -0.26
     organising
    -0.26
     afford
    -0.26
    measure
    -0.24
    -comm
    -0.24
    POSITIVE LOGITS
    天åłĤ
    0.28
    äºĨåIJ§
    0.27
    å¹»
    0.26
    UED
    0.26
    itt
    0.25
    URAL
    0.25
     implies
    0.25
    çŁ£
    0.24
    sse
    0.24
     char
    0.24
    Activations Density 0.007%

    No Known Activations