© 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. 25-TRANSCODER-HP
    7. 107854
    Prev
    Next
    INDEX
    Explanations

    funding and support

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_25.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.25.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    å¼Ĥ
    -0.29
    ç£ħ
    -0.26
    imest
    -0.26
     táºŃn
    -0.26
    åĬ£åĬ¿
    -0.26
    çĬ¶åħĥ
    -0.25
    anguard
    -0.24
    lag
    -0.24
     cháy
    -0.24
    æĿ¡ä»¶ä¸ĭ
    -0.24
    POSITIVE LOGITS
     generosity
    0.31
     Region
    0.30
     kindness
    0.28
    rina
    0.27
    adena
    0.27
    åı£æ°´
    0.26
    -region
    0.26
    RY
    0.26
    æľ¬äºĭ
    0.26
     collective
    0.25
    Activations Density 1.003%

    No Known Activations