© 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. 14-TRANSCODER-HP
    7. 39835
    Prev
    Next
    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_14.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.14.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    åį«çĶŁ
    -0.31
    ara
    -0.26
    WF
    -0.25
    忾
    -0.25
    æıŃ示
    -0.25
    å²ģ
    -0.24
    客è§Ĥ
    -0.24
    ä¹ĭ称
    -0.24
    era
    -0.24
    çĪ½
    -0.24
    POSITIVE LOGITS
    ToBounds
    0.29
    éĤ£åıª
    0.28
    åĪ¹éĤ£
    0.26
    ,:,:
    0.26
    iers
    0.25
    _Left
    0.24
     refere
    0.24
     recursively
    0.24
     MainForm
    0.24
     Ä°nsan
    0.24
    Activations Density 0.262%

    No Known Activations