© 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. 8948
    Prev
    Next
    INDEX
    Explanations

    em

    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
    åĩłæŃ¥
    -0.29
    vron
    -0.25
    abet
    -0.25
    irectional
    -0.24
    è¡©
    -0.24
    yard
    -0.24
    ifact
    -0.24
    affles
    -0.24
    containers
    -0.24
    estro
    -0.24
    POSITIVE LOGITS
    åīįæıIJæĺ¯
    0.25
     tink
    0.24
     Jain
    0.24
    éĿ¢ä¸Ĭ
    0.23
     bro
    0.23
    bh
    0.23
    /software
    0.23
    å¸ĥ
    0.23
    ä¸Ĭå¸Ĥåħ¬åı¸
    0.23
    tek
    0.23
    Activations Density 0.002%

    No Known Activations