© 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. 30-TRANSCODER-HP
    7. 95799
    Prev
    Next
    INDEX
    Explanations

    under

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_30.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.30.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rets
    -0.26
     triggered
    -0.26
    æį¨
    -0.25
    ÑĪен
    -0.25
    åıĹéĤĢ
    -0.24
    avy
    -0.24
    urette
    -0.24
     Guerrero
    -0.24
    âĺŁ
    -0.23
     clipping
    -0.23
    POSITIVE LOGITS
     investigation
    0.36
     Investigation
    0.31
    è°ĥæŁ¥
    0.30
    inspection
    0.29
     consideration
    0.28
    à¹Īา
    0.27
    磫
    0.26
     lie
    0.26
     study
    0.26
    éĶ»çĤ¼
    0.26
    Activations Density 0.883%

    No Known Activations