© 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. 121899
    Prev
    Next
    INDEX
    Explanations

    HTML code

    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
     foreseeable
    -0.07
    しっ
    -0.07
    ично
    -0.07
    雹
    -0.07
    贯穿
    -0.07
    逐一
    -0.07
    移到
    -0.07
     sürekli
    -0.07
     hồi
    -0.07
    通用
    -0.07
    POSITIVE LOGITS
    חשש
    0.07
    tolua
    0.07
    华尔街
    0.07
     Not
    0.07
    אוגוס
    0.07
     Mak
    0.07
     kardeş
    0.07
    印象
    0.07
     nadzie
    0.07
    -aff
    0.07
    Activations Density 0.050%

    No Known Activations