© 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. 32-TRANSCODER-HP
    7. 43826
    Prev
    Next
    INDEX
    Explanations

    education-related questions

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_32.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.32.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    è·ij
    -0.36
     internal
    -0.30
     run
    -0.30
     passed
    -0.28
    exter
    -0.28
     ran
    -0.28
    æ¶ĪèĢĹ
    -0.27
    è·ijäºĨ
    -0.27
     rac
    -0.27
     Internal
    -0.26
    POSITIVE LOGITS
     THR
    0.27
    éŀł
    0.26
    èĭ¦èĭ¦
    0.24
    NL
    0.24
    ehr
    0.24
     tôn
    0.24
    (Pos
    0.24
    å«Į
    0.23
     Emb
    0.23
    ipi
    0.23
    Activations Density 0.004%

    No Known Activations