© 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. 42045
    Prev
    Next
    INDEX
    Explanations

    been

    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
    WND
    -0.08
    uron
    -0.07
    站在
    -0.07
     femin
    -0.07
     glad
    -0.07
     juvenile
    -0.07
    _BTN
    -0.07
     believer
    -0.07
     newValue
    -0.07
    (bs
    -0.07
    POSITIVE LOGITS
    .Scope
    0.07
     diffs
    0.07
    rag
    0.07
     wifi
    0.07
    传奇里面
    0.06
     DARK
    0.06
    )")
    0.06
    	layout
    0.06
    	code
    0.06
    歸
    0.06
    Activations Density 0.116%

    No Known Activations