© 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. 88474
    Prev
    Next
    INDEX
    Explanations

    descriptions of groups

    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
    ACA
    -0.31
     dip
    -0.30
     bat
    -0.29
    aca
    -0.28
    tee
    -0.28
    æĭħ
    -0.26
    AMI
    -0.26
    åī²
    -0.26
    edly
    -0.26
    acas
    -0.25
    POSITIVE LOGITS
    ','.
    0.26
    _DEFINED
    0.26
    gran
    0.25
     constructed
    0.25
     EINA
    0.24
     Evans
    0.24
    olvers
    0.23
    éĻī
    0.23
     MAV
    0.23
    __.__
    0.23
    Activations Density 0.007%

    No Known Activations