© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 23-TRANSCODER-HP
    7. 23772
    Prev
    Next
    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_23.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.23.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ).\
    -0.26
    伤çĹħ
    -0.25
    allet
    -0.25
    åĪłéĻ¤
    -0.24
     ))↵
    -0.24
    ;\↵
    -0.24
     deleteUser
    -0.24
    çĶ¨æīĭ
    -0.24
    çĿ£ä¿ĥ
    -0.24
    arl
    -0.24
    POSITIVE LOGITS
    æĪIJåĬŁçİĩ
    0.27
    hci
    0.27
     uk
    0.26
    ạp
    0.26
    acting
    0.26
    PathComponent
    0.26
    以ä¸ĭ
    0.25
     success
    0.25
    letal
    0.25
    Subjects
    0.25
    Activations Density 0.003%

    No Known Activations