© 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. 7-RESID-POST-AA
    11. 78853
    Prev
    Next
    INDEX
    Explanations

    processor

    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_7/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    .*;↵
    -0.09
    ᄎ
    -0.08
     участие
    -0.08
     компью
    -0.07
    objet
    -0.07
     đòi
    -0.07
    orted
    -0.07
    _extraction
    -0.07
    𝐘
    -0.07
    igth
    -0.07
    POSITIVE LOGITS
     binnen
    0.07
    תקן
    0.07
     squared
    0.07
    avenport
    0.07
     موجود
    0.07
     بدون
    0.07
    泥土
    0.06
     Terrace
    0.06
     Gaussian
    0.06
     Eaton
    0.06
    Activations Density 0.073%

    No Known Activations