© 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. 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. 54691
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
     wizard
    -0.07
     wordt
    -0.07
    _SOURCE
    -0.07
    твержден
    -0.06
    大爷
    -0.06
     earners
    -0.06
    .Spring
    -0.06
     poster
    -0.06
    _pars
    -0.06
    author
    -0.06
    POSITIVE LOGITS
    見た
    0.07
    基
    0.07
    检测
    0.07
    整体
    0.07
    ⋪
    0.07
    ṭ
    0.07
    迥
    0.07
     이미
    0.07
    FromBody
    0.07
    =v
    0.07
    Activations Density 0.178%

    No Known Activations