© 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. 8328
    Prev
    Next
    INDEX
    Explanations

    random website content

    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
     des
    -0.49
    Des
    -0.36
    des
    -0.35
     de
    -0.34
    eps
    -0.31
     Des
    -0.29
    éĤ£äºĽ
    -0.29
    _des
    -0.28
     Deserialize
    -0.27
    isis
    -0.26
    POSITIVE LOGITS
    atories
    0.35
    té
    0.29
    ñe
    0.27
     yok
    0.26
    reator
    0.25
    IVEN
    0.25
    çīĮ
    0.25
    ILINE
    0.24
    -ok
    0.24
    $I
    0.24
    Activations Density 0.005%

    No Known Activations