© 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
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Qwen2.5-7B-IT
    4. Resid Post - 131k
    5. 19-RESID-POST-AA
    6. 8663
    Prev
    Next
    INDEX
    Explanations

    Baseball bases

    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
    ты
    -0.08
     marry
    -0.08
    ạp
    -0.07
    _iff
    -0.07
     Telerik
    -0.07
    门外
    -0.07
    越
    -0.07
    вид
    -0.07
     accuse
    -0.07
     llvm
    -0.06
    POSITIVE LOGITS
     parental
    0.07
     Bart
    0.07
    ]['
    0.07
    𝚆
    0.07
    derabad
    0.07
    	Schema
    0.06
    迫切
    0.06
    王者荣耀
    0.06
     apartheid
    0.06
     HERO
    0.06
    Activations Density 0.001%

    No Known Activations