© 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. 9979
    Prev
    Next
    INDEX
    Explanations

    quotation mark

    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
     Prostitutas
    -0.08
    ō
    -0.08
    ,UnityEngine
    -0.08
    纯电动
    -0.08
     pathetic
    -0.07
     levitra
    -0.07
    _VO
    -0.07
     mosquito
    -0.07
     이렇게
    -0.07
    quito
    -0.07
    POSITIVE LOGITS
     helf
    0.08
     wid
    0.08
    影像
    0.07
    ABB
    0.07
     aft
    0.07
     如果
    0.07
    十几
    0.06
     shelter
    0.06
     territory
    0.06
     freight
    0.06
    Activations Density 0.003%

    No Known Activations