© 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. 9-TRANSCODER-HP
    7. 29910
    Prev
    Next
    INDEX
    Explanations

    psychiat

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_9.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.9.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Grey
    -0.26
    _letters
    -0.25
     joke
    -0.25
    å¯ĵæĦı
    -0.24
     Heights
    -0.24
    å¿ĥçIJĨåѦ
    -0.24
    omed
    -0.24
    -hidden
    -0.23
    çī¢è®°
    -0.23
    akk
    -0.23
    POSITIVE LOGITS
    交éĶĻ
    0.25
    perimental
    0.25
    çĬ¬
    0.25
    INLINE
    0.24
    /plugin
    0.24
     strand
    0.24
    Ľ
    0.24
    inction
    0.24
     ple
    0.24
     perk
    0.24
    Activations Density 1.453%

    No Known Activations