© 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. 149797
    Prev
    Next
    INDEX
    Explanations

    play

    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
    ä¹łæĥ¯
    -0.30
     organisers
    -0.27
     Phonetic
    -0.27
    habit
    -0.27
     Worth
    -0.27
     purs
    -0.27
    æĭĽå¾ħ
    -0.26
    FileVersion
    -0.26
    rit
    -0.26
     Habit
    -0.25
    POSITIVE LOGITS
    ullah
    0.31
    åIJ¹
    0.27
    lyn
    0.27
    对æİ¥
    0.27
    ãĤ«ãĥ©
    0.27
    iquement
    0.26
    åºķå±Ĥ
    0.26
     mass
    0.25
    reen
    0.24
    éĶĢåĶ®é¢Ŀ
    0.24
    Activations Density 0.209%

    No Known Activations