© 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. 112324
    Prev
    Next
    INDEX
    Explanations

    friends

    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
    ìĦľ
    -0.27
    otros
    -0.27
    ç§ij
    -0.26
    mania
    -0.25
    kÅĤad
    -0.24
    èĭij
    -0.24
    .disconnect
    -0.24
    ório
    -0.24
    acements
    -0.23
    subpackage
    -0.23
    POSITIVE LOGITS
     (
    0.39
     (>
    0.29
     (^
    0.29
    ï¼Ī
    0.29
     (č↵
    0.28
    (eq
    0.28
     (âĪ
    0.28
    鹪
    0.27
    (The
    0.26
     (?)
    0.26
    Activations Density 0.002%

    No Known Activations