© 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. 24-TRANSCODER-HP
    7. 150786
    Prev
    Next
    INDEX
    Explanations

    are/is

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_24.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.24.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    mind
    -0.26
    ä¸Ģ次æĢ§
    -0.26
     sanity
    -0.26
    两次
    -0.26
    seat
    -0.25
     wearer
    -0.25
    -seat
    -0.25
    -roll
    -0.24
    ä¸Ģ次
    -0.24
    genic
    -0.24
    POSITIVE LOGITS
    Used
    0.32
     Recommended
    0.32
    å±ij
    0.32
    åı¯çĶ¨äºİ
    0.31
    çļĦæľīæķĪ
    0.30
    Recommended
    0.30
     recommended
    0.30
    _used
    0.29
     Used
    0.29
     used
    0.28
    Activations Density 1.041%

    No Known Activations