© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Qwen2.5-7B-IT
    7. Resid Post - 131k
    9. 15-RESID-POST-AA
    11. 28388
    Prev
    Next
    INDEX
    Explanations

    辭

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Rect
    -0.07
    perf
    -0.07
    はじ
    -0.07
    .free
    -0.07
    .Av
    -0.07
     Directions
    -0.07
    תחילת
    -0.07
    measurement
    -0.06
     alum
    -0.06
     initState
    -0.06
    POSITIVE LOGITS
    🐙
    0.07
     cautious
    0.06
    (|
    0.06
    nown
    0.06
     unconventional
    0.06
    (k
    0.06
    꾼
    0.06
    יכון
    0.06
     Wroc
    0.06
    ана
    0.06
    Activations Density 0.009%

    No Known Activations