© 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. 129602
    Prev
    Next
    INDEX
    Explanations

    employ

    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
    obs
    -0.26
    gest
    -0.25
    çľĭæ¸ħ
    -0.24
    赢家
    -0.24
    Gear
    -0.24
    adj
    -0.24
    çĩĥæ²¹
    -0.23
    éĿŀ常åĸľæ¬¢
    -0.23
    Inside
    -0.23
    ĻĤ
    -0.22
    POSITIVE LOGITS
    ÑĩаÑĤ
    0.27
    ered
    0.26
    asm
    0.25
    åIJİèĢħ
    0.25
    ozo
    0.25
    dcc
    0.25
    åı¦
    0.24
    inar
    0.24
    edReader
    0.24
    ASM
    0.24
    Activations Density 0.163%

    No Known Activations