© 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. 7-RESID-POST-AA
    11. 8915
    Prev
    Next
    INDEX
    Explanations

    ^

    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
     Хотя
    -0.07
    ho
    -0.07
     japanese
    -0.07
    �
    -0.07
    Φ
    -0.07
    fa
    -0.07
     ser
    -0.07
     постоя
    -0.06
     best
    -0.06
     strongest
    -0.06
    POSITIVE LOGITS
     onCreateOptionsMenu
    0.07
    物料
    0.07
     transitions
    0.07
    ionale
    0.07
     cout
    0.07
     drilled
    0.07
     wedge
    0.07
     Notebook
    0.07
     mView
    0.07
    acyj
    0.07
    Activations Density 0.005%

    No Known Activations