© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 39608
    Prev
    Next
    INDEX
    Explanations

    Regular expressions

    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
    缵
    -0.08
    起重
    -0.08
    尴
    -0.07
    ꡕ
    -0.07
    alette
    -0.06
    Honestly
    -0.06
    ddie
    -0.06
     you
    -0.06
    矧
    -0.06
     Guang
    -0.06
    POSITIVE LOGITS
    bury
    0.07
     работу
    0.07
     SAVE
    0.07
    _DIFF
    0.07
     sometimes
    0.07
    Untitled
    0.07
    血压
    0.07
    外围
    0.07
     önemli
    0.07
    歩いて
    0.06
    Activations Density 0.012%

    No Known Activations