© 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. 96700
    Prev
    Next
    INDEX
    Explanations

    Book

    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
    ished
    -0.26
     Proud
    -0.26
    ish
    -0.26
     disposable
    -0.25
    pit
    -0.25
     Stamp
    -0.25
     stacked
    -0.25
    -budget
    -0.24
    _prefs
    -0.24
    æĤ¬æµ®
    -0.24
    POSITIVE LOGITS
    erset
    0.32
    è¿ĩçļĦ
    0.29
    eft
    0.29
    å°±è¿ij
    0.27
    ä¸ĢéĿ¢
    0.26
     xuyên
    0.26
    åĩĨåĪĻ
    0.26
    æĥ°
    0.25
    LER
    0.25
    åĢ¦
    0.24
    Activations Density 0.005%

    No Known Activations