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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    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. 15-RESID-POST-AA
    6. 46216
    Prev
    Next
    INDEX
    Explanations

    decay

    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
    "text
    -0.07
     виде
    -0.07
    ued
    -0.07
     MonoBehaviour
    -0.07
    brief
    -0.07
    orizontal
    -0.07
     Omn
    -0.07
     StatefulWidget
    -0.06
                        	
    -0.06
    oller
    -0.06
    POSITIVE LOGITS
     decay
    0.08
    ניח
    0.08
     secured
    0.07
    能夠
    0.07
    laws
    0.07
    PACE
    0.07
    /column
    0.06
    _seen
    0.06
    רו
    0.06
    dating
    0.06
    Activations Density 0.002%

    No Known Activations