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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Qwen2.5-7B-IT
    4. Resid Post - 131k
    5. 15-RESID-POST-AA
    6. 26929
    Prev
    Next
    INDEX
    Explanations

    needs and requirements

    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
    定价
    -0.07
     siti
    -0.07
     ingredient
    -0.07
    深情
    -0.07
    .codigo
    -0.06
    .capitalize
    -0.06
     endorse
    -0.06
    .blank
    -0.06
    募集资金
    -0.06
     bisa
    -0.06
    POSITIVE LOGITS
    etz
    0.07
     prueba
    0.07
    感染
    0.07
    essel
    0.07
    catch
    0.07
     Mapper
    0.07
    terr
    0.07
     getInfo
    0.07
    ymbol
    0.07
    _Model
    0.07
    Activations Density 0.188%

    No Known Activations