© 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. 25-TRANSCODER-HP
    7. 108861
    Prev
    Next
    INDEX
    Explanations

    similarity

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_25.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.25.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    çľĭå¾Ĺ
    -0.30
    å¤ļå¹´çļĦ
    -0.26
    宸
    -0.25
    å¾½
    -0.24
    æĸ°çĶŁ
    -0.24
    paramref
    -0.24
    luetooth
    -0.24
    è¿Ļ个éĹ®é¢ĺ
    -0.24
    ложен
    -0.24
    èĩ³æѤ
    -0.23
    POSITIVE LOGITS
     similar
    0.42
     analogous
    0.38
     Similar
    0.35
    ä»»ä½ķ
    0.35
     comparable
    0.35
    çĽ¸ä¼¼
    0.34
    类似
    0.34
    类似çļĦ
    0.31
     any
    0.30
    similar
    0.30
    Activations Density 0.948%

    No Known Activations