© 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. 48492
    Prev
    Next
    INDEX
    Explanations

    team

    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
    雯
    -0.07
     Decor
    -0.07
    相當
    -0.07
    彝
    -0.07
    领导小组
    -0.07
    “And
    -0.07
    änn
    -0.07
     provides
    -0.07
     tails
    -0.06
    笔试
    -0.06
    POSITIVE LOGITS
    弦
    0.07
    naz
    0.07
    .utc
    0.07
    elapsed
    0.07
    -centric
    0.07
    bz
    0.06
    قاعدة
    0.06
    cio
    0.06
     PLA
    0.06
     fandom
    0.06
    Activations Density 0.031%

    No Known Activations