© 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. 28212
    Prev
    Next
    INDEX
    Explanations

    vertical arrangement

    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
     younger
    -0.07
    سنة
    -0.07
     לקרא
    -0.07
    烘焙
    -0.07
     earning
    -0.07
    SCRIBE
    -0.07
    さらに
    -0.07
    这种事情
    -0.07
    .onload
    -0.06
     unsure
    -0.06
    POSITIVE LOGITS
     Histor
    0.08
    偃
    0.07
    lua
    0.07
     ierr
    0.07
    洁白
    0.07
    _PROVID
    0.06
    Please
    0.06
    ("---
    0.06
     PdfP
    0.06
    情况进行
    0.06
    Activations Density 0.015%

    No Known Activations