© 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. 27-TRANSCODER-HP
    7. 56736
    Prev
    Next
    INDEX
    Explanations

    the

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_27.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.27.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    orama
    -0.27
    å®īåİ¿
    -0.27
    -court
    -0.25
     ÑģеÑĢии
    -0.25
     court
    -0.25
    zig
    -0.25
    ];↵↵↵
    -0.24
     seminar
    -0.24
    åĿł
    -0.24
     courtroom
    -0.24
    POSITIVE LOGITS
    人çĶŁ
    0.30
    iya
    0.28
     chiff
    0.28
    çĶŁ
    0.27
    pieces
    0.26
    SelectedItem
    0.26
    çĶŁåij½
    0.25
     çĶŁ
    0.25
    æĭĪ
    0.25
    éģ¥
    0.24
    Activations Density 0.010%

    No Known Activations