© 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. 11-RESID-POST-AA
    6. 86808
    Prev
    Next
    INDEX
    Explanations

    Ransomware and digital hostage

    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_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     breaking
    -0.07
    中に
    -0.07
    छ
    -0.07
     Reflect
    -0.07
    多余的
    -0.07
     праздник
    -0.06
     이를
    -0.06
    午
    -0.06
    riv
    -0.06
     Contribution
    -0.06
    POSITIVE LOGITS
     ctl
    0.08
    	link
    0.07
     dbContext
    0.07
    Parms
    0.07
    .KeyEvent
    0.07
     sever
    0.07
    风控
    0.07
    _authenticated
    0.07
    CI
    0.07
    乌克
    0.07
    Activations Density 0.038%

    No Known Activations