Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 41569
    Prev
    Next
    INDEX
    Explanations

    appeared

    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
    ocomplete
    -0.07
    obutton
    -0.07
    ynchronization
    -0.07
    分泌
    -0.07
    pid
    -0.07
     אלף
    -0.07
    换届
    -0.07
    PID
    -0.07
    ERRU
    -0.07
    ประสง
    -0.07
    POSITIVE LOGITS
     Iris
    0.07
    ⋆
    0.07
     Mia
    0.07
     Criterion
    0.07
     уровня
    0.07
    (rules
    0.07
     '|
    0.06
     gunmen
    0.06
     pouvoir
    0.06
    (':
    0.06
    Activations Density 0.012%

    No Known Activations