© 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. 39904
    Prev
    Next
    INDEX
    Explanations

    Instructions/Commands

    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
     RaisePropertyChanged
    -0.08
    	Spring
    -0.08
    샹
    -0.08
    unbind
    -0.07
    参数
    -0.07
    幢
    -0.07
    isky
    -0.07
     derivatives
    -0.07
    -redux
    -0.07
    샬
    -0.07
    POSITIVE LOGITS
     earthly
    0.08
    /me
    0.07
     Apex
    0.07
     seo
    0.07
    TU
    0.07
    规模
    0.07
    ᓫ
    0.07
    kap
    0.07
     Application
    0.07
    _Z
    0.06
    Activations Density 0.088%

    No Known Activations