Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Qwen2.5-7B-IT
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 29997
    Prev
    Next
    INDEX
    Explanations

    oper

    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_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    _TAGS
    -0.07
     Surf
    -0.07
     backs
    -0.07
    oblins
    -0.07
     rifle
    -0.07
     catalog
    -0.07
     dile
    -0.06
     similarity
    -0.06
    -human
    -0.06
    cılık
    -0.06
    POSITIVE LOGITS
     CONNECTION
    0.07
     lettuce
    0.07
    .Wrap
    0.07
    .System
    0.07
    뚜
    0.07
     Justiça
    0.07
     intermitt
    0.06
    鎏
    0.06
     inner
    0.06
    חוויה
    0.06
    Activations Density 0.000%

    No Known Activations