© 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. 39967
    Prev
    Next
    INDEX
    Explanations

    of

    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
    .lu
    -0.28
     Decom
    -0.26
    éĻĨ
    -0.26
    çĥĪ
    -0.25
    tri
    -0.25
    fullName
    -0.24
    å±Ĭ
    -0.24
     fullName
    -0.24
    ître
    -0.24
    使åij½æĦŁ
    -0.24
    POSITIVE LOGITS
    //{{
    0.28
    åĪ°åºķæĺ¯
    0.26
    ips
    0.26
     McB
    0.26
    eldon
    0.25
    å¯Ħ
    0.25
     warrants
    0.25
    æĹłè®ºå¦Ĥä½ķ
    0.24
    odox
    0.24
    .cgi
    0.24
    Activations Density 0.143%

    No Known Activations