© 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. 20615
    Prev
    Next
    INDEX
    Explanations

    was

    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
    	params
    -0.09
    polate
    -0.07
     bak
    -0.07
    	selected
    -0.07
    	when
    -0.07
    ジェ
    -0.06
     darken
    -0.06
    cion
    -0.06
    种子
    -0.06
     Cam
    -0.06
    POSITIVE LOGITS
    庐
    0.08
    徇
    0.07
    깅
    0.07
    .PLL
    0.07
     MSC
    0.07
    ////////////////////////////////////////////////////////////////////////////////↵
    0.06
    ================================================================
    0.06
     '':↵
    0.06
     giỏi
    0.06
    _RPC
    0.06
    Activations Density 0.000%

    No Known Activations