© 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 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. 2951
    Prev
    Next
    INDEX
    Explanations

    important

    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
    ينة
    -0.09
    _Back
    -0.07
    産
    -0.07
    ENTE
    -0.07
    宠爱
    -0.07
    메
    -0.07
    بة
    -0.06
    asonic
    -0.06
    /moment
    -0.06
    鼽
    -0.06
    POSITIVE LOGITS
     scaffold
    0.08
     machines
    0.07
     setups
    0.07
     Alias
    0.07
     framing
    0.06
     specifically
    0.06
     RelayCommand
    0.06
    移到
    0.06
    urgical
    0.06
    usage
    0.06
    Activations Density 0.066%

    No Known Activations