© 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. 15-RESID-POST-AA
    6. 49025
    Prev
    Next
    INDEX
    Explanations

    technology and systems

    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_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    (show
    -0.07
    ished
    -0.06
    偵
    -0.06
     cet
    -0.06
     av
    -0.06
    .op
    -0.06
    Overall
    -0.06
    /aws
    -0.06
     Dive
    -0.06
    dent
    -0.06
    POSITIVE LOGITS
    PIX
    0.07
    _fixture
    0.07
    �
    0.07
     fixture
    0.07
    enko
    0.07
     subscribing
    0.07
    ostringstream
    0.06
     scn
    0.06
    �
    0.06
    OnClickListener
    0.06
    Activations Density 0.292%

    No Known Activations