© 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. 149733
    Prev
    Next
    INDEX
    Explanations

    On

    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
    вез
    -0.27
    Central
    -0.27
    obic
    -0.26
    好åIJĹ
    -0.25
    éľ²
    -0.25
    opyright
    -0.25
    íĹĮ
    -0.25
    holes
    -0.24
    åĪ°äºĨ
    -0.24
    acje
    -0.24
    POSITIVE LOGITS
    éĸ±
    0.26
     unrelated
    0.25
    éĢ¾
    0.24
     ..."↵↵
    0.24
    ."&
    0.24
    æī£éĻ¤
    0.23
    -divider
    0.23
    "č↵č↵č↵
    0.23
     Broadcasting
    0.23
    ambre
    0.23
    Activations Density 1.056%

    No Known Activations