© 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
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Qwen2.5-7B-IT
    7. Resid Post - 131k
    9. 15-RESID-POST-AA
    11. 1305
    Prev
    Next
    INDEX
    Explanations

    seize

    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
    南山
    -0.09
     Killing
    -0.08
     đau
    -0.07
    呼叫
    -0.07
    A
    -0.07
     Truth
    -0.07
     Autumn
    -0.07
    Fuel
    -0.07
     [-
    -0.06
    (${
    -0.06
    POSITIVE LOGITS
     proceeded
    0.08
     pauses
    0.07
    ialized
    0.07
    	finally
    0.07
    镚
    0.07
    תברר
    0.07
    🅦
    0.07
    quence
    0.06
     którym
    0.06
    ᕗ
    0.06
    Activations Density 0.004%

    No Known Activations