© 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. 130165
    Prev
    Next
    INDEX
    Explanations

    turn/change

    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
    links
    -0.27
    æķĻ导
    -0.26
    rame
    -0.25
     Bene
    -0.25
    æľĢæĸ°çļĦ
    -0.25
    åIJ«
    -0.24
    èĪį
    -0.24
    ÑİÑīаÑı
    -0.24
     shifts
    -0.24
    fare
    -0.24
    POSITIVE LOGITS
    onomic
    0.26
    泺
    0.26
    izontally
    0.25
    æŀķ
    0.25
    大ä¸ĵ
    0.25
    .dsl
    0.24
    irk
    0.24
    CKET
    0.24
    çĹĩçĬ¶
    0.24
    bred
    0.23
    Activations Density 0.004%

    No Known Activations