© 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. 18-TRANSCODER-HP
    7. 89463
    Prev
    Next
    INDEX
    Explanations

    Code and technical writing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_18.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.18.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    uckles
    -0.28
    ack
    -0.26
    éĽĩä½£
    -0.25
    isce
    -0.25
            ↵        ↵        ↵
    -0.24
     explodes
    -0.24
    chants
    -0.24
    accordion
    -0.24
    chw
    -0.24
     accordion
    -0.24
    POSITIVE LOGITS
    çĿ¡
    0.27
    ique
    0.26
    æļĤ
    0.26
    IQUE
    0.24
    ç»´å°Ķ
    0.24
    ockey
    0.24
    对éĺµ
    0.24
    ä¸į幸
    0.23
     inset
    0.23
    èĻ½çĦ¶
    0.23
    Activations Density 61.194%

    No Known Activations