© 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. 8557
    Prev
    Next
    INDEX
    Explanations

    Encryption and Keys

    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
    åĪĨ解
    -0.28
    å®īåħ¨æĢ§
    -0.26
    λ
    -0.26
    WebpackPlugin
    -0.26
    ç²ĴåŃIJ
    -0.25
    held
    -0.25
    ductive
    -0.25
    ORB
    -0.25
    rxjs
    -0.24
    èĤ¢
    -0.24
    POSITIVE LOGITS
     CONF
    0.27
    ace
    0.26
    éĻħ
    0.26
    å·¡è§Ĩ
    0.26
    审
    0.25
    phet
    0.24
    pread
    0.24
     northwest
    0.24
    ollo
    0.23
    æ±ī
    0.23
    Activations Density 0.016%

    No Known Activations