© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 19-RESID-POST-AA
    11. 70015
    Prev
    Next
    INDEX
    Explanations

    underscore

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_19/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    벡
    -0.08
    vari
    -0.07
    工業
    -0.07
    "math
    -0.07
    reich
    -0.07
     gute
    -0.07
    �
    -0.07
     Trey
    -0.07
     constructions
    -0.07
    散发
    -0.07
    POSITIVE LOGITS
    等
    0.08
    의
    0.07
    �
    0.07
     Based
    0.07
     Si
    0.07
     Having
    0.07
    ה
    0.07
    𝙷
    0.07
    =n
    0.07
    等因素
    0.07
    Activations Density 0.006%

    No Known Activations