© 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. 57191
    Prev
    Next
    INDEX
    Explanations

    late

    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
     DI
    -0.26
    [at
    -0.25
     Prospect
    -0.25
    大åıĶ
    -0.25
    å¾Ģ
    -0.25
     CURL
    -0.24
    tü
    -0.24
    tür
    -0.24
    ario
    -0.24
    AGR
    -0.24
    POSITIVE LOGITS
    æĶ¾å¤§
    0.29
    mak
    0.25
    uce
    0.25
    onic
    0.25
    æĩĭ
    0.25
    _OK
    0.25
    è¿ĻäºĽéĹ®é¢ĺ
    0.25
    å¿ħ
    0.24
    oha
    0.24
    upe
    0.24
    Activations Density 0.002%

    No Known Activations