© 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. 23-RESID-POST-AA
    11. 129964
    Prev
    Next
    INDEX
    Explanations

    Ruben Amaro Jr

    np_max-act-logits · gemini-2.0-flashTriggered by @bettyfeng2003
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_23/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     recieved
    -0.07
    非常好的
    -0.06
    .isFile
    -0.06
    单纯的
    -0.06
    _cond
    -0.06
    院子
    -0.06
    	cell
    -0.06
    主持召开
    -0.06
     inserted
    -0.06
    _unpack
    -0.06
    POSITIVE LOGITS
    おります
    0.07
     accountant
    0.07
    专线
    0.07
    大使
    0.07
    ึง
    0.07
    redirectTo
    0.06
    aman
    0.06
    HOME
    0.06
    internet
    0.06
     Ltd
    0.06
    Activations Density 0.033%

    No Known Activations